© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14648
    Prev
    Next
    INDEX
    Explanations

    terms related to biographies and tributes

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

    Text related to biographies or obituaries

    np_acts-logits-general · gemini-2.0-flash

    biography and obituaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    featureID
    -0.46
    stylers
    -0.38
    RTEE
    -0.35
     relaxed
    -0.35
    atchewan
    -0.35
    DoubleQuotes
    -0.35
     Rukh
    -0.35
     мәкал
    -0.34
    oulli
    -0.34
    schemes
    -0.34
    POSITIVE LOGITS
     OBITUARY
    1.15
     Obituary
    0.90
    Obituary
    0.82
    ituaries
    0.81
     obituary
    0.73
    ituary
    0.69
    脚注の使い方
    0.63
    PyExc
    0.60
    +#+#
    0.60
    ThroughAttribute
    0.60
    Activations Density 0.023%

    No Known Activations