© 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. 36-GEMMASCOPE-RES-16K
    11. 8011
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms and court-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JpaRepository
    -0.45
    Jîn
    -0.45
    WebControls
    -0.44
     المعيارى
    -0.43
    ніципалі
    -0.42
    ClientSize
    -0.41
    etsk
    -0.37
     상세
    -0.36
    MigrationBuilder
    -0.35
     inclin
    -0.35
    POSITIVE LOGITS
     Utah
    1.47
    Utah
    1.40
     Salt
    1.28
     utah
    1.22
    Salt
    1.21
     Provo
    1.11
     LDS
    1.10
     BYU
    1.09
     Mormon
    1.02
    SALT
    1.01
    Activations Density 0.349%

    No Known Activations