© 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. 31-GEMMASCOPE-RES-131K
    6. 38284
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions, particularly focusing on files, graphics, threads, and data structures

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

    file and device names

    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
    .
    -0.37
     if
    -0.26
    ↵↵
    -0.25
     because
    -0.25
     solches
    -0.25
     something
    -0.25
     it
    -0.24
    ↵
    -0.24
     sesuatu
    -0.23
     loob
    -0.23
    POSITIVE LOGITS
     nahilalakip
    1.25
    ValueStyle
    1.23
     ProtoMessage
    1.09
     Infórmanos
    1.09
    parsedMessage
    1.03
    Tembelea
    1.02
     surla
    1.00
    ⸫
    0.98
    MLLoader
    0.97
     autorytatywna
    0.96
    Activations Density 0.156%

    No Known Activations