© 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. 69590
    Prev
    Next
    INDEX
    Explanations

    terms related to higher-order statistics and their implications in various contexts

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

    higher-order

    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
     surla
    -0.68
     يتيمه
    -0.65
     الحره
    -0.54
     вікісторінку
    -0.54
    hoeddwyd
    -0.50
    ValueStyle
    -0.47
    WithMany
    -0.47
     Biôgrafia
    -0.46
     censiti
    -0.45
    VYMaps
    -0.44
    POSITIVE LOGITS
     higher
    2.16
    higher
    1.95
     lower
    1.86
    Higher
    1.76
     Higher
    1.69
     HIGHER
    1.61
    lower
    1.55
     höheren
    1.41
     höher
    1.38
     upper
    1.32
    Activations Density 0.369%

    No Known Activations