Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3813
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical appearances, particularly related to hair, eyes, and body type

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.51
    ThroughAttribute
    -0.50
    sproble
    -0.49
     Geiger
    -0.49
     AsyncTask
    -0.48
    حياتها
    -0.48
    atchewan
    -0.48
    saraba
    -0.47
    sprogram
    -0.47
    Carriera
    -0.47
    POSITIVE LOGITS
     bangs
    0.76
     messy
    0.70
     Mess
    0.68
     waves
    0.66
    Mess
    0.65
     wavy
    0.64
     buns
    0.62
     curls
    0.62
     braids
    0.61
     hairstyles
    0.61
    Activations Density 0.109%

    No Known Activations