© 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. 43985
    Prev
    Next
    INDEX
    Explanations

    opening and closing braces and parentheses in code

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

    inheritance and parent classes

    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
    IntoConstraints
    -0.54
    Derbyniad
    -0.50
    +#+#
    -0.49
    WebElementEntity
    -0.49
     contrasted
    -0.45
    Климаты
    -0.45
     متعلقه
    -0.44
    ConstraintMaker
    -0.44
     artesanía
    -0.44
    ValueStyle
    -0.43
    POSITIVE LOGITS
    Superclass
    0.53
     super
    0.52
     inheritance
    0.51
    脚注の使い方
    0.50
     inherited
    0.50
    super
    0.49
     父
    0.49
    父
    0.48
     parent
    0.48
     father
    0.47
    Activations Density 0.007%

    No Known Activations