© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7540
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to legal proceedings and courtroom activities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    permission or allowance

    np_acts-logits-general · gemini-2.0-flash

    authorization allowed

    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
    Negative Logits
     MainAxisSize
    -0.45
    inSlope
    -0.42
     thiệu
    -0.41
     initComponents
    -0.41
     ciber
    -0.37
    arschijnlijk
    -0.37
    ReusableCell
    -0.36
     <>",
    -0.35
    ýt
    -0.35
    SaveChangesAsync
    -0.34
    POSITIVE LOGITS
     allowed
    1.92
     permitted
    1.80
     Allowed
    1.71
    allowed
    1.66
    Allowed
    1.55
     allowable
    1.48
     ALLOWED
    1.47
    permitted
    1.39
     permissible
    1.38
     permitido
    1.33
    Activations Density 0.785%

    No Known Activations