© 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. 90712
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions for CSS file manipulation

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

    extract or minify

    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
     WALT
    -0.41
    resizingMask
    -0.41
     Barns
    -0.40
     Relief
    -0.40
     Fer
    -0.39
    ómicas
    -0.39
    inton
    -0.38
     tolerance
    -0.38
    tolerance
    -0.38
     Mercy
    -0.37
    POSITIVE LOGITS
     Extract
    0.63
    Extract
    0.62
     препратки
    0.62
     extract
    0.61
     extractor
    0.59
    Extraction
    0.59
     extraction
    0.59
    extract
    0.58
     extracting
    0.58
    extraction
    0.54
    Activations Density 0.001%

    No Known Activations