© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 64311
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports outcomes and match results

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

    game outcomes

    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
    findElement
    -0.47
     intra
    -0.40
    $_['
    -0.39
     lang
    -0.39
     Na
    -0.39
    PCell
    -0.39
     dre
    -0.39
     va
    -0.39
    getItemId
    -0.39
     te
    -0.38
    POSITIVE LOGITS
     Савезне
    0.54
     transfieras
    0.51
     miniaturka
    0.50
    guiente
    0.49
     kebenaran
    0.48
     nadzie
    0.48
    ślę
    0.48
    ConstraintMaker
    0.47
     @}
    0.47
    LookAnd
    0.47
    Activations Density 0.012%

    No Known Activations