© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 70886
    Prev
    Next
    INDEX
    Explanations

    references to personal attributes and biographical details of individuals

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

    controversies and awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    TargetApi
    -0.36
    component
    -0.34
     clc
    -0.33
    DialogContent
    -0.32
    舐
    -0.31
    ์ต
    -0.31
     pihaknya
    -0.31
     postIndex
    -0.31
    stående
    -0.31
    情节
    -0.30
    POSITIVE LOGITS
     controversies
    0.68
     Contro
    0.55
     Awards
    0.55
     Controversy
    0.55
     awards
    0.55
    Awards
    0.54
     controversy
    0.53
    Controversy
    0.52
    Contro
    0.52
     Net
    0.52
    Activations Density 0.002%

    No Known Activations