© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6071
    Prev
    Next
    INDEX
    Explanations

    mentions of people, particularly names or identifiers

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

    Japanese words ending in "ズ" or "ミ" after a Katakana word

    np_acts-logits-general · gemini-2.0-flash

    アズサ アズミ ジェミニ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    st
    -0.53
    est
    -0.50
    set
    -0.48
    dat
    -0.46
    ın
    -0.45
    ing
    -0.45
    un
    -0.44
    reif
    -0.44
    sem
    -0.43
     produced
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.81
    reportWebVitals
    0.78
    ロウィン
    0.76
    featureID
    0.74
    parsedMessage
    0.73
    aarrggbb
    0.72
    RegressionTest
    0.71
    ificance
    0.70
    ThroughAttribute
    0.70
    enumii
    0.69
    Activations Density 0.031%

    No Known Activations