© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104700
    Prev
    Next
    INDEX
    Explanations

    discussions related to legal instructions and findings in court cases

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

    Punctuation marks (especially periods) that indicate the end of sentences, paragraphs, or sections in formal academic and legal writing.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amb
    -0.42
     ret
    -0.40
     bund
    -0.39
     normal
    -0.38
    nodoc
    -0.38
    Jeografia
    -0.37
    amb
    -0.37
     Gila
    -0.36
     GMP
    -0.36
     equ
    -0.36
    POSITIVE LOGITS
    ViewFeatures
    0.62
    addCriterion
    0.57
     Gnade
    0.55
    BeginContext
    0.53
    exitRule
    0.53
    oredCriteria
    0.52
    ſelf
    0.50
     publicação
    0.50
     bluzka
    0.49
     jsPsych
    0.49
    Activations Density 0.130%

    No Known Activations