© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6075
    Prev
    Next
    INDEX
    Explanations

    references to female offspring or daughters and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stow
    -0.75
     defaultstate
    -0.72
    swick
    -0.70
    matsu
    -0.70
    esgue
    -0.70
     Leck
    -0.70
    kus
    -0.70
    zeitige
    -0.68
     salud
    -0.67
    aldi
    -0.64
    POSITIVE LOGITS
     filles
    1.20
     girls
    1.07
     daughters
    1.02
     Oda
    0.98
    UGHTER
    0.96
    girls
    0.92
     fille
    0.92
     Girls
    0.90
    Girls
    0.90
     datter
    0.86
    Activations Density 0.054%

    No Known Activations