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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 6574
    Prev
    Next
    INDEX
    Explanations

    components and factors related to water quality and biological analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     BoxFit
    -0.60
    Immigration
    -0.59
     Immigration
    -0.58
    Porsche
    -0.56
    unknownFields
    -0.54
    帖最后由
    -0.54
    glio
    -0.53
    UpInside
    -0.53
     cend
    -0.53
    ItemBackground
    -0.52
    POSITIVE LOGITS
     drinking
    1.35
     Drinking
    1.17
    Drinking
    1.16
    drinking
    1.06
     water
    1.03
     potable
    1.02
     DRINK
    1.02
     drink
    0.92
    drink
    0.90
     Water
    0.90
    Activations Density 0.127%

    No Known Activations