© 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. 1328
    Prev
    Next
    INDEX
    Explanations

    references to logging frameworks and libraries in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     виправивши
    -0.64
    ModelAdmin
    -0.57
    GraphicsUnit
    -0.54
    ReusableCell
    -0.52
    
    -0.49
    SourceChecksum
    -0.49
     createState
    -0.48
    principalColumn
    -0.47
    CreateModel
    -0.46
    jsxFileName
    -0.46
    POSITIVE LOGITS
    slf
    0.67
     miniaturka
    0.50
     zoude
    0.48
    zbęd
    0.47
    prefixer
    0.47
    retmen
    0.47
     wikipagina
    0.47
     indépend
    0.46
     المعيارى
    0.46
    fastjson
    0.46
    Activations Density 0.015%

    No Known Activations