© 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. 30-GEMMASCOPE-RES-16K
    11. 10773
    Prev
    Next
    INDEX
    Explanations

    sequences that resemble computer code or data artifacts

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

    Characters and symbols in code or data

    np_acts-logits-general · gemini-2.0-flash

    LPS, CAD, ISO, CL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arno
    -0.41
     Ard
    -0.39
     Arena
    -0.38
     Arnold
    -0.37
    ap
    -0.37
    Ap
    -0.37
     arena
    -0.36
    Arena
    -0.36
     ар
    -0.36
    apu
    -0.36
    POSITIVE LOGITS
     ffilmiau
    0.57
    KommentareTeilen
    0.54
    utives
    0.54
    DeleteBehavior
    0.54
    下载附件
    0.54
    ⓧ
    0.53
     kaarangay
    0.52
     Aztec
    0.52
     Italijani
    0.51
    脚注の使い方
    0.51
    Activations Density 0.231%

    No Known Activations