© 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. 107302
    Prev
    Next
    INDEX
    Explanations

    HTML header and formatting tags used in documents

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

    funding and keywords

    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
    Dabei
    -0.33
     nomme
    -0.30
     humain
    -0.30
     farlo
    -0.29
     candidatos
    -0.28
     humanas
    -0.28
     `
    -0.28
     verdaderas
    -0.28
     vraie
    -0.28
     vrai
    -0.28
    POSITIVE LOGITS
    <strong>
    0.88
     disambiguazione
    0.78
     للاسماء
    0.76
    تقاوى
    0.73
     Италијани
    0.73
    IVEREF
    0.73
    rungsseite
    0.71
    WebElementEntity
    0.70
    InitVars
    0.69
    دانشنامهٔ
    0.68
    Activations Density 0.000%

    No Known Activations