© 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. 31-GEMMASCOPE-RES-131K
    11. 10209
    Prev
    Next
    INDEX
    Explanations

    instances of the word "or" and related variations

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

    alternatives or multiple options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     either
    -0.38
    either
    -0.35
    InputBorder
    -0.35
    Démographie
    -0.34
    sional
    -0.33
    xampp
    -0.32
    TEMPLATES
    -0.32
     li
    -0.32
    Either
    -0.31
    erschein
    -0.31
    POSITIVE LOGITS
    複数
    0.70
     Infórmanos
    0.69
     plusieurs
    0.68
     mehreren
    0.67
     flera
    0.65
     multiple
    0.64
     meerdere
    0.64
    หลาย
    0.64
     mehrere
    0.62
    複数の
    0.62
    Activations Density 0.035%

    No Known Activations