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. 10335
    Prev
    Next
    INDEX
    Explanations

    instances of citations and references

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

    names following "by"

    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
    WebServlet
    -0.39
    ่านั้น
    -0.35
     democrá
    -0.32
     solchen
    -0.31
     imágen
    -0.30
     siècles
    -0.30
     متعلقه
    -0.30
     pestaña
    -0.29
     Configuración
    -0.29
    Przypisy
    -0.29
    POSITIVE LOGITS
     stockbilder
    0.61
     Italijani
    0.59
     Infórmanos
    0.59
    estacks
    0.59
    ⪜
    0.57
     ſans
    0.56
    tisgarh
    0.56
     Bharat
    0.55
     ویکی‌پدی
    0.54
    ྑ
    0.54
    Activations Density 0.191%

    No Known Activations