© 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. 7270
    Prev
    Next
    INDEX
    Explanations

    references to an individual named Dan

    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
    يميديا
    -0.82
     Monfieur
    -0.79
     Smokey
    -0.72
     Bourg
    -0.72
    aine
    -0.72
     Huey
    -0.70
    Földrajzportál
    -0.69
     Vicksburg
    -0.69
    addGap
    -0.68
    ^(@)
    -0.68
    POSITIVE LOGITS
     Dan
    3.13
    Dan
    2.98
     DAN
    2.32
    dan
    2.32
     dan
    2.30
    DAN
    2.21
     Daniel
    1.45
     Dani
    1.45
     Danilo
    1.39
    Dani
    1.33
    Activations Density 0.066%

    No Known Activations