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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16195
    Prev
    Next
    INDEX
    Explanations

    the term "well" and its variations throughout the text

    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
     Schaefer
    -0.78
    ობ
    -0.70
    ᾶ
    -0.67
    icksburg
    -0.67
    cifix
    -0.66
    dci
    -0.64
    TableBody
    -0.63
     Titans
    -0.63
     Brü
    -0.61
     Giordano
    -0.61
    POSITIVE LOGITS
     well
    2.93
     WELL
    2.50
    well
    2.48
     Well
    2.48
    Well
    2.45
    WELL
    2.13
     wells
    1.98
    wells
    1.69
     Wells
    1.57
     bien
    1.53
    Activations Density 0.076%

    No Known Activations