© 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. 3085
    Prev
    Next
    INDEX
    Explanations

    technical terms and data structures related to programming and software development

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

    code or programming-related tokens like file paths, programming language keywords, and function names.

    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
    RenderAtEndOf
    -1.27
     $_(
    -1.11
    AddTagHelper
    -1.08
     MainAxisSize
    -1.07
    ſſung
    -1.05
    <unused74>
    -1.04
     zwiſchen
    -1.04
    <unused14>
    -1.04
    [@BOS@]
    -1.04
    <unused8>
    -1.04
    POSITIVE LOGITS
    .
    0.49
    ?
    0.36
     Stirn
    0.34
    ,
    0.34
     is
    0.33
    ;
    0.32
     tombe
    0.31
     instead
    0.31
    </h2>
    0.29
     compromisos
    0.28
    Activations Density 0.386%

    No Known Activations