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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2785
    Prev
    Next
    INDEX
    Explanations

    references to quotes and specific phrases associated with racial or societal issues

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

    words in quotes

    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
     beira
    -0.30
     nă
    -0.30
     pinulongan
    -0.29
    OGND
    -0.28
    Cuánto
    -0.28
    تقاوى
    -0.28
     AssemblyVersion
    -0.28
    原始内容存档于
    -0.27
     énon
    -0.26
     wireType
    -0.26
    POSITIVE LOGITS
     experts
    0.76
    uxxxx
    0.70
    ésultats
    0.70
    experts
    0.69
    jokes
    0.68
    joke
    0.67
    
    0.66
    <unused30>
    0.66
    iſchen
    0.65
    <unused19>
    0.65
    Activations Density 0.059%

    No Known Activations