© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13998
    Prev
    Next
    INDEX
    Explanations

    relevant details and identifiers related to publications and reports

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

    Tokens followed by punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    numeric separators and symbols

    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
     kasarigan
    -0.76
     للمعارف
    -0.69
    tvguidetime
    -0.65
     Geſch
    -0.59
    MigrationBuilder
    -0.57
    بالإنجليزية
    -0.57
    ."],
    -0.57
    хіво
    -0.57
     Waſſer
    -0.56
    MENAFN
    -0.55
    POSITIVE LOGITS
     |
    1.06
     /
    0.81
     -
    0.66
    |
    0.63
     •
    0.62
     ||
    0.61
     ·
    0.60
     –
    0.60
     ::
    0.56
     &
    0.55
    Activations Density 1.094%

    No Known Activations