Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129992
    Prev
    Next
    INDEX
    Explanations

    key terms related to email organization and user interaction

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

    quickly locate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.57
    MLLoader
    -0.57
    ArgsConstructor
    -0.56
    DMETHOD
    -0.55
    TypedDataSet
    -0.54
    ThroughAttribute
    -0.52
    RTGC
    -0.51
     metav
    -0.51
    modelBuilder
    -0.50
    ########.
    -0.50
    POSITIVE LOGITS
     quickly
    1.04
     rápidamente
    0.97
     quick
    0.91
    Quickly
    0.91
    quickly
    0.88
     locate
    0.85
     rapidamente
    0.85
     schnell
    0.85
     Quickly
    0.83
     cepat
    0.78
    Activations Density 0.036%

    No Known Activations