© 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. 68444
    Prev
    Next
    INDEX
    Explanations

    references to ancient geography and early human migrations

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

    mammoth steppe, maxilla, land bridge

    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
    featureID
    -0.55
    UrlResolution
    -0.55
    الحياه
    -0.50
     GenerationType
    -0.50
     surla
    -0.49
    AccessorTable
    -0.48
    IContainer
    -0.46
    WithIOException
    -0.45
    TestBed
    -0.45
    cipar
    -0.44
    POSITIVE LOGITS
    omla
    0.40
     الو
    0.39
    Gazette
    0.39
    AnimationFrame
    0.38
     étoit
    0.38
    Chart
    0.38
    Literatuur
    0.38
    CORN
    0.37
    ztő
    0.36
    wieś
    0.36
    Activations Density 0.106%

    No Known Activations