© 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. 31-GEMMASCOPE-RES-131K
    11. 5839
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, especially those associated with file operations and digital I/O functions

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

    <start_of_turn>user prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.50
    ьаж
    -0.43
    BagConstraints
    -0.40
    -------------</
    -0.39
     ObjectParameter
    -0.39
    хьтан
    -0.38
    delwed
    -0.37
    bootstrapcdn
    -0.36
    matchCondition
    -0.36
    dAtA
    -0.36
    POSITIVE LOGITS
     Sketch
    0.61
     sketch
    0.57
    Sketch
    0.56
    Serial
    0.56
     Arduino
    0.55
     sketches
    0.54
     Serial
    0.53
     digital
    0.49
     Digital
    0.49
    sketch
    0.49
    Activations Density 0.166%

    No Known Activations