© 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. 1547
    Prev
    Next
    INDEX
    Explanations

    words and suffixes indicating medical or legal terminology

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

    technical or specialized terminology with suffixes like "-atory", "-ys", or words related to specific technical/legal domains.

    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
    frac
    -0.53
    withIdentifier
    -0.53
    alış
    -0.52
    hspace
    -0.51
    woff
    -0.50
    ът
    -0.50
    følgelig
    -0.50
    (“
    -0.49
    MENAFN
    -0.49
    fahan
    -0.49
    POSITIVE LOGITS
    y
    0.93
    ey
    0.85
    ety
    0.82
    yyyy
    0.82
    ry
    0.81
    yyy
    0.78
    edy
    0.76
    ky
    0.75
     Arty
    0.75
    eky
    0.74
    Activations Density 0.704%

    No Known Activations