© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9242
    Prev
    Next
    INDEX
    Explanations

    references to male and female gender differences in various contexts

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

    Male/female distinctions

    np_acts-logits-general · gemini-2.0-flash

    male/femalegender

    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
     صوتيه
    -0.59
    ViewFeatures
    -0.53
    HasAnnotation
    -0.46
    </thead>
    -0.45
    tagHelperRunner
    -0.45
    ClassNotFound
    -0.45
     jadx
    -0.45
    SuccessListener
    -0.44
    vismo
    -0.44
    pidou
    -0.43
    POSITIVE LOGITS
     women
    2.61
     male
    2.61
     female
    2.49
     females
    2.47
     males
    2.43
    male
    2.16
    Male
    2.10
     Female
    2.10
    female
    2.08
     Females
    2.07
    Activations Density 0.820%

    No Known Activations