© 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. 1658
    Prev
    Next
    INDEX
    Explanations

    innovative ideas and inventions as well as their key contributors

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

    historical inventions and their inventors, with a focus on the year and details of the innovation.

    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
     our
    -0.31
    Somebody
    -0.29
     we
    -0.29
     alın
    -0.28
    Our
    -0.27
    Someone
    -0.26
    We
    -0.26
    </b>
    -0.26
    default
    -0.26
    お互
    -0.26
    POSITIVE LOGITS
     himself
    1.14
    himself
    1.07
     himſelf
    0.93
    EndContext
    0.86
     zijne
    0.80
     ModelExpression
    0.80
    MessageOf
    0.79
    ftagPool
    0.76
     Himself
    0.75
     surla
    0.75
    Activations Density 0.538%

    No Known Activations