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. 4-GEMMASCOPE-RES-16K
    6. 597
    Prev
    Next
    INDEX
    Explanations

    references to the name "Dan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BaseActivity
    -0.55
    يميديا
    -0.54
     Vuitton
    -0.54
     mö
    -0.53
    gó
    -0.53
    Oye
    -0.52
    Pragma
    -0.52
     Vertra
    -0.51
     upo
    -0.50
     Visconti
    -0.50
    POSITIVE LOGITS
     Dan
    2.14
    Dan
    2.04
     DAN
    1.81
     dan
    1.76
    DAN
    1.66
    dan
    1.55
     Daniel
    1.48
    Daniel
    1.34
     Dani
    1.34
     Danilo
    1.27
    Activations Density 0.110%

    No Known Activations