© 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. 81995
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate ongoing or initiating actions

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

    continuing or starting actions

    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
     producing
    -0.85
     celebrating
    -0.82
     playing
    -0.82
     viviendo
    -0.81
     perdiendo
    -0.81
     selling
    -0.80
     bringing
    -0.80
     creating
    -0.80
     creciendo
    -0.80
     supplying
    -0.79
    POSITIVE LOGITS
     kasarigan
    0.45
     to
    0.41
     nevoie
    0.39
     силь
    0.32
     how
    0.31
     sorts
    0.31
    گون
    0.31
    尽
    0.31
    세요
    0.31
     tribute
    0.30
    Activations Density 0.083%

    No Known Activations