© 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. 20-GEMMASCOPE-RES-131K
    6. 58072
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures and operations

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

    programming and multilingual text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     near
    -0.36
     broadly
    -0.33
     required
    -0.33
    душка
    -0.32
     a
    -0.32
     far
    -0.31
     early
    -0.31
     briefly
    -0.31
     explicitly
    -0.30
     involved
    -0.30
    POSITIVE LOGITS
    
    0.79
    GOTREF
    0.77
    TagMode
    0.75
     <=",
    0.73
    queryInterface
    0.72
     للاسماء
    0.69
     ویکی‌پدی
    0.69
     oprot
    0.69
     autorytatywna
    0.68
    +#+#
    0.66
    Activations Density 0.004%

    No Known Activations