© 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. 12563
    Prev
    Next
    INDEX
    Explanations

    references to accountability or responsibility in contexts involving people or organizations

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

    on behalf of

    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
     distinguish
    -0.87
    distingu
    -0.83
     differentiate
    -0.80
     distinguishing
    -0.79
     disting
    -0.77
     Differenti
    -0.75
     differentiating
    -0.75
    differ
    -0.74
     distingu
    -0.72
    Differenti
    -0.72
    POSITIVE LOGITS
     behalf
    0.77
     part
    0.73
     parte
    0.62
     часть
    0.57
    part
    0.56
     część
    0.54
     Teil
    0.54
     onderdeel
    0.54
    Бахар
    0.53
     bagian
    0.52
    Activations Density 0.013%

    No Known Activations