© 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. 5086
    Prev
    Next
    INDEX
    Explanations

    versioning information, specifically related to major, minor, build, and revision numbers

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

    Major and Minor versions

    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
     BoxDecoration
    -0.50
     ویکی‌پدی
    -0.48
    ollectionView
    -0.45
    IntoConstraints
    -0.44
    elemField
    -0.43
    webElementXpaths
    -0.43
     חיצוניים
    -0.41
     estekak
    -0.39
     ब्रेकडाउन
    -0.38
    сылкі
    -0.38
    POSITIVE LOGITS
    Major
    1.56
    major
    1.43
     Major
    1.41
    MAJOR
    1.34
     major
    1.30
     MAJOR
    1.27
    Minor
    1.09
    minor
    1.06
     Minor
    1.00
     MINOR
    0.92
    Activations Density 0.015%

    No Known Activations