© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8758
    Prev
    Next
    INDEX
    Explanations

    references to judicial proceedings and legal terminology

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

    section headings and structural divisions in legal documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.52
    +#+
    -0.52
    ruik
    -0.49
     للاسماء
    -0.47
    EndInit
    -0.46
    Autoritní
    -0.45
    ➋
    -0.45
     Bioaccumulative
    -0.44
    alek
    -0.43
    TokenNameLBRACE
    -0.42
    POSITIVE LOGITS
     II
    0.81
     III
    0.80
    II
    0.73
    III
    0.71
    Section
    0.64
     IV
    0.62
     Section
    0.60
    SECTION
    0.60
     VIII
    0.57
     section
    0.56
    Activations Density 0.625%

    No Known Activations