© 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. 20-GEMMASCOPE-RES-16K
    11. 10376
    Prev
    Next
    INDEX
    Explanations

    references to a male subject or pronouns related to masculinity

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

    third-person masculine pronouns referring to a male subject.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the pronoun "He" (or "he") when referring to a male person in the text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     поро
    -0.47
    umet
    -0.46
    orari
    -0.45
     the
    -0.45
    atag
    -0.44
    razine
    -0.44
    uating
    -0.44
    ereal
    -0.44
     standard
    -0.43
    tazione
    -0.43
    POSITIVE LOGITS
    himself
    0.91
     himself
    0.85
     he
    0.82
     Himself
    0.75
    He
    0.71
     He
    0.71
     zijne
    0.70
     beliau
    0.70
     그의
    0.67
     kanyang
    0.66
    Activations Density 0.250%

    No Known Activations