© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 61448
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of crucial information or advice

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

    best, easiest, gold standard

    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
     ModelExpression
    -0.91
    setVerticalGroup
    -0.66
    帖最后由
    -0.62
    fjspx
    -0.55
     referenties
    -0.55
    enumii
    -0.53
    RegistryLite
    -0.51
    Vidite
    -0.50
    Personendaten
    -0.50
    IsMutable
    -0.48
    POSITIVE LOGITS
     best
    1.80
     easiest
    1.68
    best
    1.49
     quickest
    1.43
    最好的
    1.34
     safest
    1.31
     fastest
    1.25
    Best
    1.25
     بهترین
    1.21
     najleps
    1.20
    Activations Density 0.075%

    No Known Activations