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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 11864
    Prev
    Next
    INDEX
    Explanations

    references to the name "David."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hant
    -0.80
     pant
    -0.73
    /#/
    -0.68
     Reichen
    -0.66
     poffe
    -0.66
     UNT
    -0.65
     Winslow
    -0.64
    antee
    -0.63
     sure
    -0.63
    ’?
    -0.63
    POSITIVE LOGITS
     David
    1.41
    David
    1.32
    DAVID
    1.25
     DAVID
    1.19
     Davids
    1.17
     david
    1.10
    david
    1.05
     Davie
    1.01
     Davido
    0.95
    avid
    0.95
    Activations Density 0.048%

    No Known Activations