© 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. 39478
    Prev
    Next
    INDEX
    Explanations

    references to serious topics and deeper meanings in discussions

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

    judgments about each other

    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
     bowiem
    -0.35
     tega
    -0.35
     perhaps
    -0.33
     amado
    -0.33
     essentially
    -0.31
     siquiera
    -0.31
     newest
    -0.30
     seemingly
    -0.30
    nieuw
    -0.30
    ="&#
    -0.30
    POSITIVE LOGITS
    WebElementEntity
    0.68
    =$?
    0.65
    bootstrapcdn
    0.65
    EndGlobalSection
    0.63
     estekak
    0.62
    WaitGroup
    0.62
    ituary
    0.61
    writeFieldEnd
    0.60
     @"/
    0.60
    IndentedString
    0.60
    Activations Density 0.071%

    No Known Activations