© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 18058
    Prev
    Next
    INDEX
    Explanations

    references to Odds Ratios (OR) in statistical analysis

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

    OR, ORR, odds ratio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initializeApp
    -0.58
    transQ
    -0.58
    fjspx
    -0.55
    weightedMode
    -0.54
    AddHtmlAttribute
    -0.53
    PostExecute
    -0.48
    twimg
    -0.47
    SCAPE
    -0.47
    tagHelperRunner
    -0.47
    demie
    -0.46
    POSITIVE LOGITS
     OR
    2.05
    OR
    1.48
     Or
    1.09
    Or
    0.93
     oppure
    0.81
     or
    0.80
     hoặc
    0.78
     Orr
    0.75
    or
    0.74
     AND
    0.72
    Activations Density 0.012%

    No Known Activations