© 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. 475
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to programming and system configuration

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

    programming or code-related tokens and syntax elements.

    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
     idéia
    -0.57
    ToScroll
    -0.52
    OGND
    -0.51
     dAtA
    -0.50
    ismet
    -0.48
    
    -0.48
    writeFieldEnd
    -0.48
     NSCoder
    -0.48
    currentColor
    -0.47
    tvguidetime
    -0.47
    POSITIVE LOGITS
     Houſe
    0.48
    
    0.48
    WindowConstants
    0.42
     menu
    0.40
     houſe
    0.40
     itſelf
    0.39
     haer
    0.38
    Menu
    0.38
    侍
    0.37
     Menu
    0.37
    Activations Density 0.619%

    No Known Activations