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. 93461
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their circumstances related to existence or identity

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

    quantity of people or things

    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
     terecht
    -0.32
    ニュアル
    -0.27
     peine
    -0.27
     najlep
    -0.27
    intah
    -0.27
     stället
    -0.27
     giây
    -0.27
     höchst
    -0.26
    ことができます
    -0.26
     gratuito
    -0.26
    POSITIVE LOGITS
     plenty
    1.06
    Plenty
    1.02
    plenty
    0.99
     Plenty
    0.99
    เยอะ
    0.94
     plentiful
    0.86
     많
    0.85
     abound
    0.79
     many
    0.78
     lots
    0.78
    Activations Density 0.035%

    No Known Activations