© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 995
    Prev
    Next
    INDEX
    Explanations

    class and method declarations in programming

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

    programming-related keywords and code structures, particularly in class and method definitions across different programming languages.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    complexContent
    -0.60
    EDEFAULT
    -0.60
    ConstraintMaker
    -0.60
     propOrder
    -0.60
    HtmlAttribute
    -0.58
    Personendaten
    -0.58
    badlogic
    -0.54
    DockStyle
    -0.54
    تفصیلات
    -0.54
     ModelExpression
    -0.54
    POSITIVE LOGITS
    OrderService
    0.34
     unum
    0.32
     manipulation
    0.32
    utuhkan
    0.30
     @"/
    0.30
    file
    0.30
    }{*}{}
    0.30
     desk
    0.29
    voice
    0.29
    astanza
    0.28
    Activations Density 0.356%

    No Known Activations