© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12108
    Prev
    Next
    INDEX
    Explanations

    emotional and experiential aspects of human interactions and challenges

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

    action verbs and their subjects

    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
    ̈́
    -0.75
     surla
    -0.68
    EndContext
    -0.66
    Referanser
    -0.60
    SequentialGroup
    -0.60
    новништво
    -0.58
    usermodel
    -0.58
     ModelExpression
    -0.57
    makeConstraints
    -0.57
     fashiola
    -0.57
    POSITIVE LOGITS
     things
    0.58
     without
    0.55
     something
    0.53
     rather
    0.50
     everything
    0.49
     what
    0.43
     dingen
    0.43
    ;
    0.42
    ,
    0.42
     while
    0.39
    Activations Density 0.114%

    No Known Activations