© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10639
    Prev
    Next
    INDEX
    Explanations

    terms related to hierarchy and categorization

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

    before certain suffixes or codes (e.g., redis client, her fellow)

    np_acts-logits-general · gemini-2.0-flash

    male resist pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    ➯
    -0.55
    rativa
    -0.53
    QMetaType
    -0.49
    principalColumn
    -0.48
    Биография
    -0.48
     Praga
    -0.46
     cortes
    -0.46
     contextLoads
    -0.45
     chapa
    -0.45
     Japón
    -0.44
    POSITIVE LOGITS
     mijne
    0.56
    équi
    0.55
    usammen
    0.52
     gevol
    0.49
     الاح
    0.48
     kjø
    0.47
    ßerdem
    0.47
    rboles
    0.46
     dezelve
    0.46
    المنا
    0.45
    Activations Density 1.735%

    No Known Activations