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

    Neuronpedia

    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. 10852
    Prev
    Next
    INDEX
    Explanations

    keywords related to driving offenses and vehicle licensing issues

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

    "license"

    np_acts-logits-general · gemini-2.0-flash

    license trainer

    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
    MigrationBuilder
    -0.61
     يتيمه
    -0.60
     ffilmiau
    -0.52
    省市镇
    -0.50
    OGND
    -0.47
     propOrder
    -0.46
    IsMutable
    -0.44
    byshev
    -0.43
    ITHUB
    -0.42
    المكان
    -0.41
    POSITIVE LOGITS
     license
    1.73
     License
    1.52
     licence
    1.49
    license
    1.37
    License
    1.34
     plate
    1.34
     plates
    1.33
     licenses
    1.31
     Licence
    1.29
     licensing
    1.23
    Activations Density 0.088%

    No Known Activations