© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 121819
    Prev
    Next
    INDEX
    Explanations

    occurrences of underscores in technical or programming contexts

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

    user commission backend

    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
     ویکی‌پدی
    -0.92
    parsedMessage
    -0.81
    ItemBackground
    -0.79
     '\\;'
    -0.79
     betweenstory
    -0.75
     насељу
    -0.75
    ScopeManager
    -0.74
    IBOutlet
    -0.73
    SourceChecksum
    -0.73
    sidemargin
    -0.72
    POSITIVE LOGITS
    _
    0.44
    ↵
    0.36
     
    0.36
     also
    0.35
     in
    0.35
     (
    0.34
    -
    0.34
    <
    0.32
     s
    0.32
     https
    0.31
    Activations Density 0.018%

    No Known Activations