Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 4410
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    1.3%
    1068
    +0.13
    0.8%
    1757
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1376
    +0.20
    0.08
    1068
    +0.13
    0.07
    814
    +0.12
    0.07
    Negative Logits
    <bos>
    -3.37
    ⓧ
    -0.72
    /***
    
    -0.69
    Referanser
    -0.64
    
    
    -0.61
     per
    -0.60
     државе
    -0.58
    Хро
    -0.58
    Kontrola
    -0.58
    /*!
    
    -0.58
    POSITIVE LOGITS
     maneu
    1.46
     sappi
    1.39
     ricardo
    1.39
     stockholm
    1.36
     peugeot
    1.34
     affor
    1.34
     increa
    1.33
     Minang
    1.32
     lamborghini
    1.31
     maroc
    1.30
    Activations Density 0.191%

    No Known Activations