© 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. 121422
    Prev
    Next
    INDEX
    Explanations

    references to assembly metadata and licensing information

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

    disclaimers of warranty

    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
     GenerationType
    -0.86
    MLLoader
    -0.79
    featureID
    -0.76
    FunctionFlags
    -0.73
    RefNanny
    -0.71
    AutoScaleMode
    -0.70
    djangoproject
    -0.70
    parsedMessage
    -0.65
    RenderAtEndOf
    -0.64
    IndentedString
    -0.64
    POSITIVE LOGITS
     AssemblyCompany
    2.20
     الحره
    1.52
    VIAF
    1.23
    Autoritní
    1.16
     VIAF
    1.15
     AssemblyTitle
    1.14
    Normdaten
    0.93
     ISNI
    0.80
    ApplicationTests
    0.79
    labelledby
    0.67
    Activations Density 0.001%

    No Known Activations