© 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. 24737
    Prev
    Next
    INDEX
    Explanations

    specific references to subjects, objects, or properties, particularly in scientific or legal contexts

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

    chosen nouns, appointed, purchased

    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
    enumi
    -0.41
    ziel
    -0.35
    گاب
    -0.30
     Nes
    -0.30
    hod
    -0.30
    hin
    -0.28
    TagMode
    -0.28
    CELLANEOUS
    -0.27
    ٰ
    -0.26
    datatype
    -0.25
    POSITIVE LOGITS
     purchased
    0.79
     appointed
    0.72
     gekozen
    0.71
     recém
    0.71
    購入した
    0.71
    newly
    0.71
     chosen
    0.71
     znajdu
    0.71
     nominated
    0.71
     hired
    0.71
    Activations Density 0.235%

    No Known Activations