© 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. 58759
    Prev
    Next
    INDEX
    Explanations

    elements and terms related to physical structures and mechanics

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

    physical structures and materials

    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
     noDo
    -0.54
     vectorielles
    -0.52
    TypedDataSet
    -0.51
     ivelany
    -0.49
    IUrlHelper
    -0.49
    AsUp
    -0.48
     ſtand
    -0.46
     Comprometido
    -0.46
    MessageOf
    -0.46
     vectorielle
    -0.45
    POSITIVE LOGITS
    insch
    0.47
     punch
    0.40
     }}"></
    0.36
     Alembic
    0.35
     zostać
    0.35
    tigny
    0.35
    getahuan
    0.34
    الثة
    0.34
    HttpSession
    0.34
    bigl
    0.34
    Activations Density 0.053%

    No Known Activations