© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8259
    Prev
    Next
    INDEX
    Explanations

    instances of the word "comment" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.63
    afficheront
    -0.52
    yi
    -0.52
    ars
    -0.50
    ly
    -0.48
    erne
    -0.47
     Off
    -0.47
    pc
    -0.46
    Cec
    -0.46
    ers
    -0.46
    POSITIVE LOGITS
     commentaries
    0.96
    ValueStyle
    0.94
    migrationBuilder
    0.92
     commentary
    0.91
     Statement
    0.91
     Commentary
    0.90
    Commentary
    0.88
     Statements
    0.86
    IntoConstraints
    0.84
    commented
    0.83
    Activations Density 0.103%

    No Known Activations