© 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. 20-GEMMASCOPE-RES-131K
    11. 106201
    Prev
    Next
    INDEX
    Explanations

    references to emails, actions related to email management, and operations within a software context

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

    import, receiver, action, RX, code, math, plurals

    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
     otomatig
    -0.66
    OGND
    -0.56
     <=",
    -0.54
    ⤹
    -0.50
     autorytatywna
    -0.43
    Viitteet
    -0.39
     AssemblyVersion
    -0.39
     okuyayım
    -0.38
     تضيفلها
    -0.38
    فایل‌لار
    -0.38
    POSITIVE LOGITS
    AndEndTag
    0.56
     Amadeus
    0.47
     Holtz
    0.45
    setFlags
    0.45
    LONDON
    0.44
    jsdelivr
    0.44
    openzeppelin
    0.44
    mtrl
    0.44
    meren
    0.43
     pstmt
    0.42
    Activations Density 0.196%

    No Known Activations