© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8487
    Prev
    Next
    INDEX
    Explanations

    references to various forms of the word "man."

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

    "Man" or "man" followed by other tokens

    np_acts-logits-general · gemini-2.0-flash

    man followed by words and names

    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
    CloseOperation
    -0.96
    Šaltiniai
    -0.69
     оригіналу
    -0.69
    PhysRevD
    -0.69
     betweenstory
    -0.69
     للمعارف
    -0.68
    BURGH
    -0.66
    VersionUID
    -0.66
     محفوظة
    -0.66
    rawDesc
    -0.63
    POSITIVE LOGITS
     Man
    0.70
    Man
    0.68
     MAN
    0.65
     man
    0.58
    Mano
    0.58
    Kind
    0.56
    made
    0.55
    man
    0.55
     ман
    0.52
    cipation
    0.51
    Activations Density 0.106%

    No Known Activations