© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 76420
    Prev
    Next
    INDEX
    Explanations

    instances of closing parentheses and brackets in code snippets

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

    closing parenthesis followed by code

    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
     juicio
    -0.35
     '/';
    -0.32
     автомо
    -0.32
    yorsunuz
    -0.31
    sprogramm
    -0.31
    zunehmen
    -0.31
     Flas
    -0.31
    écou
    -0.31
    bedür
    -0.31
     persön
    -0.30
    POSITIVE LOGITS
    posedge
    0.69
     '\\;'
    0.65
    expandindo
    0.64
    ⓧ
    0.60
    хьтан
    0.59
     ब्रेकडाउन
    0.56
    enterOuterAlt
    0.56
    المناصب
    0.55
     صوتيه
    0.55
     autorytatywna
    0.55
    Activations Density 0.022%

    No Known Activations