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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5431
    Prev
    Next
    INDEX
    Explanations

    references to showering and bathing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagLayout
    -0.68
     مرئيه
    -0.63
    jsonwebtoken
    -0.57
    makeConstraints
    -0.54
    UnsafeEnabled
    -0.54
     Roskov
    -0.52
    ffine
    -0.50
     autorytatywna
    -0.49
     صوتيه
    -0.49
     Manajemen
    -0.48
    POSITIVE LOGITS
     washing
    0.81
     wash
    0.79
     soap
    0.74
     jabón
    0.73
     bathing
    0.69
     washes
    0.69
     Wash
    0.69
     WASH
    0.68
     bath
    0.67
     Washing
    0.67
    Activations Density 0.220%

    No Known Activations