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. 22-GEMMASCOPE-RES-16K
    6. 10331
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names associated with medical professionals and their credentials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Mill," "Miller," or "Mills."

    np_acts-logits-general · gemini-2.0-flash

    Nicholas Mills, Miller

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barbosa
    -0.67
    PDO
    -0.63
     FontWeight
    -0.62
    Barb
    -0.59
     Barbarian
    -0.59
     Vandal
    -0.58
     PDO
    -0.57
     Barb
    -0.54
     Selva
    -0.53
     Thebes
    -0.53
    POSITIVE LOGITS
     Mill
    2.17
    Mill
    2.04
     Miller
    2.00
    MILL
    1.92
     Mil
    1.92
     MILL
    1.88
     mill
    1.88
     MIL
    1.85
    Miller
    1.84
    mill
    1.83
    Activations Density 0.298%

    No Known Activations