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. 20-GEMMASCOPE-RES-16K
    6. 2929
    Prev
    Next
    INDEX
    Explanations

    components and features related to home appliance repair and maintenance

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

    Appliance or machine components

    np_acts-logits-general · gemini-2.0-flash

    washing machine operation states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    évaluateur
    -0.64
     bogotá
    -0.63
     ſame
    -0.60
     Púb
    -0.60
    хали
    -0.58
     showers
    -0.57
    Архівовано
    -0.57
     ſever
    -0.56
     Goat
    -0.56
    Искәрмәләр
    -0.56
    POSITIVE LOGITS
     lid
    0.59
     user
    0.56
    ComponentName
    0.52
     programma
    0.50
    Demografia
    0.49
     appliance
    0.49
    Lid
    0.48
     model
    0.48
     chamber
    0.48
     program
    0.47
    Activations Density 0.180%

    No Known Activations