© 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. 3248
    Prev
    Next
    INDEX
    Explanations

    repeated patterns involving the number '1' and associated activations

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

    mathematical or computational notation, such as numbers, indices, mathematical symbols, and references to scientific publications.

    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
    BibitemShut
    -0.73
    ьаж
    -0.69
    RenderAtEndOf
    -0.68
     >=",
    -0.67
     resourceCulture
    -0.67
    <bos>
    -0.65
     كومونز
    -0.63
     Autorizaciones
    -0.60
     ''.
    -0.60
    ésultats
    -0.60
    POSITIVE LOGITS
    1
    0.96
    १
    0.42
    １
    0.40
    Tril
    0.40
    esModule
    0.39
    ১
    0.38
    topLeft
    0.38
     eleven
    0.36
    btnNew
    0.36
    Lily
    0.35
    Activations Density 0.514%

    No Known Activations