© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4191
    Prev
    Next
    INDEX
    Explanations

    repeated references to a female subject or pronouns associated with female entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BrowserModule
    -0.53
    statechange
    -0.49
     raiſ
    -0.49
     Tinto
    -0.49
     uſed
    -0.48
    Fiat
    -0.47
     समीक्षाएं
    -0.47
     Fiat
    -0.46
     Numerade
    -0.46
     itſelf
    -0.46
    POSITIVE LOGITS
    her
    3.36
    Her
    2.97
    HER
    2.95
     Her
    2.91
     HER
    2.80
     her
    2.23
    hers
    1.65
    heri
    1.57
    herit
    1.52
     Хер
    1.48
    Activations Density 0.289%

    No Known Activations