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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14527
    Prev
    Next
    INDEX
    Explanations

    references to cloth diapers and related terms

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

    Cloth diapering and related terms

    np_acts-logits-general · gemini-2.0-flash

    cloth diapers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.79
    styleType
    -0.67
    Diwedd
    -0.56
     &___
    -0.56
    ArrowToggle
    -0.55
    HtmlAttribute
    -0.51
    RTSC
    -0.47
     AppCompatTheme
    -0.46
    ftagPool
    -0.46
     MenuView
    -0.45
    POSITIVE LOGITS
     AssemblyVersion
    0.37
    //
    0.36
     Patreon
    0.34
     referrerpolicy
    0.34
     Selbst
    0.33
    twimg
    0.33
     Inscrivez
    0.33
     bricolaje
    0.33
     Anfänger
    0.32
     forums
    0.32
    Activations Density 0.602%

    No Known Activations