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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 11653
    Prev
    Next
    INDEX
    Explanations

    elements related to aquatic activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !*\
    -0.59
     Horowitz
    -0.58
     AssemblyCulture
    -0.57
    MessageTagHelper
    -0.54
     Schen
    -0.53
     समीक्षाओं
    -0.53
    contentLoaded
    -0.52
    binder
    -0.52
    ramas
    -0.52
    penes
    -0.51
    POSITIVE LOGITS
     swim
    1.99
     swimming
    1.90
     swimmers
    1.83
     swims
    1.81
     swimmer
    1.74
     Swim
    1.71
    Swim
    1.69
     Swimming
    1.68
    swim
    1.66
    Swimming
    1.60
    Activations Density 0.206%

    No Known Activations