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. 1394
    Prev
    Next
    INDEX
    Explanations

    LaTeX package commands and related syntax elements

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

    Packages loaded in LaTeX documents

    np_acts-logits-general · gemini-2.0-flash

    latex package includes

    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
     surla
    -0.77
     متعلقه
    -0.69
    rungsseite
    -0.68
    ServletException
    -0.68
     通販
    -0.55
    openConnection
    -0.54
     ModelExpression
    -0.54
    urlpatterns
    -0.54
    WithEmail
    -0.50
    +#+#
    -0.49
    POSITIVE LOGITS
    !("{}",
    0.59
    "]);
    
    0.57
     cref
    0.56
     preamble
    0.55
    hibits
    0.53
     मद
    0.53
     zb
    0.52
    reys
    0.51
     bénéficiaire
    0.51
    lays
    0.51
    Activations Density 0.038%

    No Known Activations