© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10407
    Prev
    Next
    INDEX
    Explanations

    variations of the word "well"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.85
     Shakspeare
    -0.82
    Искәрмәләр
    -0.78
     "");
    
    -0.75
    URIComponent
    -0.75
     raiſ
    -0.74
    >`;
    -0.73
     Efq
    -0.72
     fhew
    -0.72
    >",
    
    -0.72
    POSITIVE LOGITS
     aswell
    1.44
     also
    1.23
     too
    1.15
     cũng
    0.97
     aussi
    0.95
     likewise
    0.95
     Also
    0.94
     ALSO
    0.93
    also
    0.92
    Also
    0.91
    Activations Density 0.038%

    No Known Activations