© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9053
    Prev
    Next
    INDEX
    Explanations

    processes related to sealing and covering mechanisms in various contexts

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

    phrases describing placing one object on top of or covering another object.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    fvar
    -0.54
    RTEX
    -0.47
    httphttps
    -0.47
     cuerdas
    -0.46
    
    -0.44
    mbitos
    -0.44
    RTLR
    -0.44
     zoude
    -0.44
     Amiens
    -0.43
    IndentedString
    -0.43
    POSITIVE LOGITS
     cover
    0.45
    cover
    0.44
     сверху
    0.43
     lid
    0.43
     resourceCulture
    0.43
     sealing
    0.42
    AsUp
    0.41
     VISIT
    0.40
     covering
    0.40
     encima
    0.40
    Activations Density 0.273%

    No Known Activations