© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8287
    Prev
    Next
    INDEX
    Explanations

    references to male gender or nouns related to men

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteAttribute
    -0.65
    rungsseite
    -0.62
    DataAnnotations
    -0.54
    SerializedSize
    -0.49
     getLogin
    -0.48
    Diweddarwch
    -0.44
     awakeFromNib
    -0.44
    AutoScale
    -0.43
    arraycopy
    -0.43
    transQ
    -0.43
    POSITIVE LOGITS
    men
    1.41
    man
    1.15
    woman
    1.11
    MAN
    0.98
    MEN
    0.88
    WOMAN
    0.77
    women
    0.76
    people
    0.68
    persons
    0.66
    person
    0.65
    Activations Density 0.229%

    No Known Activations