© 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. 12-GEMMASCOPE-RES-16K
    11. 5258
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, and other document structuring elements or metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.68
    UserScript
    -0.68
     outputStream
    -0.63
    parsedMessage
    -0.60
    providedIn
    -0.60
     "/";
    -0.60
    GTCX
    -0.58
    yarnpkg
    -0.58
    autoreleasepool
    -0.56
     Unger
    -0.55
    POSITIVE LOGITS
     Assoc
    0.62
     Dept
    0.60
     comfy
    0.59
     Rev
    0.59
     Corp
    0.59
     Corr
    0.58
     refs
    0.57
     Collab
    0.57
     Atty
    0.57
     Dev
    0.57
    Activations Density 1.031%

    No Known Activations