© 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. 8729
    Prev
    Next
    INDEX
    Explanations

    references to people, their roles, or achievements within various contexts

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

    Tokens after commas

    np_acts-logits-general · gemini-2.0-flash

    describing states or actions

    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
    RetentionPolicy
    -0.49
    IUrlHelper
    -0.49
     TextInputType
    -0.49
    MigrationBuilder
    -0.47
    expandindo
    -0.46
    ISupport
    -0.45
    ByVersion
    -0.44
    */),
    -0.43
    featureID
    -0.42
    ImageContext
    -0.42
    POSITIVE LOGITS
     having
    1.52
     being
    1.34
    having
    1.32
     habiendo
    1.20
    Having
    1.20
     avendo
    1.19
    being
    1.17
     Having
    1.15
     essendo
    1.03
     HAVING
    1.02
    Activations Density 0.691%

    No Known Activations