© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 515
    Prev
    Next
    INDEX
    Explanations

    clauses or statements related to programming functions and printing outputs

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

    Code involving printing or logging

    np_acts-logits-general · gemini-2.0-flash

    code list item

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    glEnd
    -0.45
    HtmlAttribute
    -0.42
    mappedBy
    -0.41
    Становништво
    -0.40
     BoxDecoration
    -0.39
     religión
    -0.39
    closePath
    -0.39
    InvalidProtocol
    -0.39
    Vtbl
    -0.37
     abstrait
    -0.36
    POSITIVE LOGITS
     وتسجيلات
    0.50
    jsxFileName
    0.49
     שוליים
    0.45
     arşivlendi
    0.44
     individually
    0.44
     Fulda
    0.43
     einzeln
    0.42
     individual
    0.42
     оригіналу
    0.42
     iconLine
    0.42
    Activations Density 0.343%

    No Known Activations