© 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. 34932
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of alternatives or uniqueness

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

    anywhere else

    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
     niti
    -0.38
    Preliminaries
    -0.34
     pem
    -0.34
    に伴
    -0.32
     porté
    -0.31
     tud
    -0.31
     Kin
    -0.31
     formed
    -0.31
    聡
    -0.31
     Pro
    -0.30
    POSITIVE LOGITS
    ValueStyle
    0.84
    MigrationBuilder
    0.81
    IsContent
    0.79
    Anywhere
    0.78
     فريبيس
    0.78
     ModelExpression
    0.76
    Jeografia
    0.76
     Anywhere
    0.74
    anywhere
    0.71
     المعيارى
    0.67
    Activations Density 0.005%

    No Known Activations