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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12906
    Prev
    Next
    INDEX
    Explanations

    negative contractions and phrases of denial or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows apostrophes or quotations

    np_acts-logits-general · gemini-2.0-flash

    won don't might

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.87
     itſelf
    -0.86
     themſelves
    -0.81
     Monfieur
    -0.81
     Chwiliwch
    -0.81
     myſelf
    -0.79
     Reſ
    -0.76
     pleaſure
    -0.68
    Spolja
    -0.68
     himſelf
    -0.68
    POSITIVE LOGITS
    P
    0.35
    <eos>
    0.33
    
    0.32
    Mag
    0.32
    .
    0.32
    Is
    0.31
     &
    0.30
    ↵↵
    0.30
    ApiOperation
    0.30
    Dec
    0.29
    Activations Density 0.111%

    No Known Activations