© 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. 30-GEMMASCOPE-RES-16K
    11. 12865
    Prev
    Next
    INDEX
    Explanations

    numerical values and identifiers related to scientific data

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

    Appears before numbers/codes

    np_acts-logits-general · gemini-2.0-flash

    catalog numbers, codes, and citations

    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
     للمعارف
    -0.82
     препратки
    -0.69
     Geſch
    -0.64
    出版年
    -0.61
    queryInterface
    -0.60
     незавершена
    -0.58
     <=",
    -0.57
    inSlope
    -0.56
    <unused68>
    -0.56
    intios
    -0.56
    POSITIVE LOGITS
    B
    0.41
    providedIn
    0.36
    R
    0.35
    E
    0.35
    A
    0.34
    BF
    0.32
    S
    0.31
    F
    0.31
    OOTDTY
    0.31
    printStackTrace
    0.30
    Activations Density 1.036%

    No Known Activations