© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3339
    Prev
    Next
    INDEX
    Explanations

    data related to demographic statistics and racial composition

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

    numerical percentages and statistics in text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.74
     Half
    -0.55
    findpost
    -0.55
    parsedMessage
    -0.55
     تضيفلها
    -0.53
    zzleHttp
    -0.52
    ########.
    -0.52
    Half
    -0.50
    SharedCtor
    -0.50
    帖最后由
    -0.50
    POSITIVE LOGITS
     percent
    1.09
     percentage
    0.99
    %
    0.97
     %
    0.94
     percentages
    0.88
    percent
    0.88
     Prozent
    0.84
    \%
    0.81
     Percent
    0.80
    Percent
    0.80
    Activations Density 0.702%

    No Known Activations