© 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. 9-GEMMASCOPE-RES-131K
    11. 50427
    Prev
    Next
    INDEX
    Explanations

    mentions of registry related to APIs

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

    registry file paths and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HttpNotFound
    -0.50
    انگلیسی
    -0.46
    djangoproject
    -0.45
    AnchorTagHelper
    -0.44
    onedDateTime
    -0.44
    zzleHttp
    -0.43
     påver
    -0.43
    cshtml
    -0.42
     fotográfico
    -0.42
    ngOn
    -0.39
    POSITIVE LOGITS
    registry
    2.94
     registry
    1.55
    Registry
    1.37
     Registry
    1.26
    regist
    0.86
     regist
    0.82
     registrar
    0.81
     REG
    0.80
     Regist
    0.79
    ISTRY
    0.75
    Activations Density 0.002%

    No Known Activations