© 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. 21-GEMMASCOPE-RES-16K
    11. 12738
    Prev
    Next
    INDEX
    Explanations

    specific terms related to technical specifications or engineering concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITBAD
    -0.58
    ArrowToggle
    -0.54
    Chham
    -0.53
    GEBURTSDATUM
    -0.52
    entration
    -0.50
    Datuak
    -0.49
     Hardly
    -0.48
     Harlow
    -0.48
    dule
    -0.48
    protoimpl
    -0.48
    POSITIVE LOGITS
    ToBounds
    0.43
    MigrationBuilder
    0.40
    rrggbb
    0.40
     domestic
    0.39
     domestically
    0.38
    UrlResolution
    0.38
    RectangleBorder
    0.37
    ローカル
    0.36
     simpler
    0.35
    CodeAttribute
    0.34
    Activations Density 1.770%

    No Known Activations