© 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. 31218
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to computation and logic problems

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

    constraints and logic programming

    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
     дописавши
    -0.67
     للاسماء
    -0.62
     ब्रेकडाउन
    -0.61
     surla
    -0.60
     الرياضيه
    -0.57
    #+#
    -0.53
    jsxFileName
    -0.53
     SDLK
    -0.52
     للمعارف
    -0.52
     TestBed
    -0.52
    POSITIVE LOGITS
    ặt
    0.42
    Chooser
    0.33
    IntoConstraints
    0.33
    ọi
    0.32
    LayoutConstraint
    0.31
    aspectRatio
    0.31
    Palmarès
    0.30
     inconn
    0.29
     incó
    0.29
    anglès
    0.28
    Activations Density 0.519%

    No Known Activations