Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 47046
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to various contexts

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

    large numbers and quantities

    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
     CanadaChoose
    -0.48
    uxxxx
    -0.47
    ronpa
    -0.44
    EndContext
    -0.43
    AndEndTag
    -0.42
     Preferencias
    -0.42
     lenker
    -0.40
     dönem
    -0.40
    <?
    -0.38
     intenciones
    -0.38
    POSITIVE LOGITS
     miles
    0.62
     crores
    0.60
     breweries
    0.55
     mics
    0.54
     monasteries
    0.53
     bots
    0.51
     mile
    0.50
     wineries
    0.49
     bikes
    0.48
    randomUUID
    0.48
    Activations Density 0.074%

    No Known Activations