© 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. 558
    Prev
    Next
    INDEX
    Explanations

    financial terms and symbols

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

    mathematical or computational notation like exponents, derivatives, and programming symbols.

    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
     fisik
    -0.52
    liceerd
    -0.51
     createSprite
    -0.51
     ACCIDENT
    -0.50
    drawSprites
    -0.49
     fisico
    -0.49
     Menschheit
    -0.47
     zima
    -0.47
     física
    -0.46
     utafitiHapana
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.45
    IUrlHelper
    0.42
    sizeCache
    0.42
    AuthContext
    0.42
    WebVitals
    0.40
     CreateTagHelper
    0.39
    TagMode
    0.39
    rawDesc
    0.38
    Hochspringen
    0.38
    endsection
    0.36
    Activations Density 1.997%

    No Known Activations