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. 24-GEMMASCOPE-RES-16K
    6. 14031
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms related to biological processes and substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding "water" (or its translations)

    np_acts-logits-general · gemini-2.0-flash

    free, drinking, or distilled water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.66
    EndGlobalSection
    -0.65
    msgTypes
    -0.61
    ChildScrollView
    -0.58
     समीक्षाओं
    -0.58
    Parcelize
    -0.58
     AssemblyCulture
    -0.57
     виправивши
    -0.57
     XCTest
    -0.57
     ivelany
    -0.56
    POSITIVE LOGITS
     water
    3.96
     Water
    3.32
    water
    3.32
    Water
    3.26
     WATER
    3.14
    WATER
    2.90
     agua
    2.53
     waters
    2.50
     Wasser
    2.46
    水
    2.46
    Activations Density 0.430%

    No Known Activations