© 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. 31416
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols used in code or programming contexts

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

    finalize writing

    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
     تضيفلها
    -0.71
    IsContent
    -0.52
     BoxDecoration
    -0.50
     NSCoder
    -0.48
     jadx
    -0.46
    getMinutes
    -0.46
    !*\
    -0.45
    GOTREF
    -0.45
     cherchés
    -0.45
    jspx
    -0.44
    POSITIVE LOGITS
    __
    2.25
    __'
    1.00
    \_\_
    0.96
    '__
    0.95
    ___
    0.93
    __]
    0.88
    "__
    0.87
    __/
    0.86
     '__
    0.85
     __
    0.85
    Activations Density 0.031%

    No Known Activations