© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 626
    Prev
    Next
    INDEX
    Explanations

    references to the "Man" prefix in various contexts

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

    the word "Man" or variations of it appearing at the beginning of proper nouns and names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parti
    -0.34
    Folge
    -0.31
    diad
    -0.30
     parti
    -0.30
     Vasco
    -0.30
    ingle
    -0.30
    Bildung
    -0.29
     Bab
    -0.29
    UserModel
    -0.28
    bige
    -0.28
    POSITIVE LOGITS
     Man
    0.74
    ConstraintMaker
    0.72
    Man
    0.71
     Manit
    0.63
    astify
    0.57
     MAN
    0.56
     マン
    0.56
    تقاوى
    0.54
    prefixer
    0.54
     man
    0.54
    Activations Density 0.182%

    No Known Activations