© 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. 23-GEMMASCOPE-RES-16K
    11. 3041
    Prev
    Next
    INDEX
    Explanations

    grammatical elements related to legal and constitutional discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonsoft
    -0.40
     rin
    -0.35
     onCancelled
    -0.34
     vital
    -0.33
     r
    -0.33
     instead
    -0.33
    RetentionPolicy
    -0.33
     Seligman
    -0.33
     bis
    -0.32
    NOPQRST
    -0.32
    POSITIVE LOGITS
     AspNetCore
    0.57
    RegressionTest
    0.56
     but
    0.53
    AutoField
    0.52
     Anſ
    0.51
    PreferredItem
    0.50
     ſta
    0.49
     אלא
    0.47
    ніципалі
    0.47
     sondern
    0.46
    Activations Density 0.538%

    No Known Activations