© 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. 11994
    Prev
    Next
    INDEX
    Explanations

    statements indicating the existence and characteristics of locations

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

    "is" or "are" followed by a description/location

    np_acts-logits-general · gemini-2.0-flash

    is followed by description

    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
     pu
    -0.36
     mili
    -0.31
     gu
    -0.30
    好的
    -0.29
     Red
    -0.29
     recovery
    -0.29
     human
    -0.29
     líqu
    -0.29
     case
    -0.29
    nice
    -0.28
    POSITIVE LOGITS
     overseen
    0.73
     surla
    0.73
     presided
    0.70
     accompanied
    0.69
    aarrggbb
    0.69
     supported
    0.68
     comprised
    0.67
     flanked
    0.64
     characterized
    0.63
     sponsored
    0.63
    Activations Density 0.948%

    No Known Activations