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. 42478
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and methods related to programming and user interface elements

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

    start_of_turn user

    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
    TagMode
    -0.66
    دانشنامهٔ
    -0.64
     iconLine
    -0.62
    Біографія
    -0.57
    BASEPATH
    -0.54
    UrlResolution
    -0.53
     Reverso
    -0.53
     cref
    -0.52
    AndEndTag
    -0.51
    thmus
    -0.50
    POSITIVE LOGITS
     stage
    0.41
     stakes
    0.40
     hemsida
    0.38
     scene
    0.35
     stake
    0.35
    stage
    0.33
     window
    0.33
    basicConfig
    0.33
     drept
    0.32
    runApp
    0.31
    Activations Density 0.001%

    No Known Activations