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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16142
    Prev
    Next
    INDEX
    Explanations

    terms related to warranties and legal disclaimers

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

    Terms related to product guarantees

    np_acts-logits-general · gemini-2.0-flash

    implied warranties and guarantees

    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
     preparatory
    -0.49
    RenderAtEndOf
    -0.45
     aspirants
    -0.45
     broth
    -0.44
     vorbereitet
    -0.44
     Dixie
    -0.43
    ernalia
    -0.43
    netes
    -0.43
    เศษ
    -0.41
     straws
    -0.41
    POSITIVE LOGITS
     warranty
    1.86
     warranties
    1.55
     Warranty
    1.50
     guarantee
    1.45
    Warranty
    1.42
    warranty
    1.41
     warran
    1.39
     garantie
    1.37
     Guarantee
    1.30
    Guarantee
    1.29
    Activations Density 0.187%

    No Known Activations