© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3378
    Prev
    Next
    INDEX
    Explanations

    references to file handling and configuration in programming contexts

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

    file paths and file-related operations in source code.

    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
    Tikang
    -0.63
     JpaRepository
    -0.62
     CURIAM
    -0.60
    transQ
    -0.60
    LookAnd
    -0.59
     صوتيه
    -0.58
    IntoConstraints
    -0.58
    
    -0.58
    addCriterion
    -0.56
    xase
    -0.56
    POSITIVE LOGITS
    zaamheid
    0.40
    querySelector
    0.36
    znál
    0.33
     where
    0.33
    kuper
    0.33
    ĩa
    0.33
    Existe
    0.32
     location
    0.32
    ような
    0.32
     bedoeld
    0.32
    Activations Density 0.162%

    No Known Activations