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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13475
    Prev
    Next
    INDEX
    Explanations

    specific quantitative or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }');
    -1.05
    ')")
    -1.02
    setVerticalGroup
    -1.02
    <bos>
    -1.00
    MigrationBuilder
    -0.99
    SourceChecksum
    -0.97
    modelBuilder
    -0.96
    styleType
    -0.96
    Personendaten
    -0.95
    }')
    -0.95
    POSITIVE LOGITS
     the
    0.65
     to
    0.59
     for
    0.56
    ,
    0.52
     that
    0.51
     in
    0.48
     a
    0.47
     an
    0.47
     either
    0.44
     at
    0.42
    Activations Density 0.842%

    No Known Activations