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. 16-GEMMASCOPE-RES-16K
    6. 12768
    Prev
    Next
    INDEX
    Explanations

    HTML elements and forms associated with user interface controls and messages

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

    HTML or formatting code

    np_acts-logits-general · gemini-2.0-flash

    bar, thickness, or message within ui elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.81
     ModelExpression
    -0.79
    principalColumn
    -0.78
     propOrder
    -0.64
    awtextra
    -0.63
    endregion
    -0.61
    ')}}">
    -0.57
    )))),
    -0.56
    posedge
    -0.56
    ')")
    -0.56
    POSITIVE LOGITS
    ontale
    0.52
    __
    0.48
     mobilité
    0.48
     Pyrenees
    0.47
     houſe
    0.47
    content
    0.47
     ſtate
    0.46
     stretch
    0.46
     ſame
    0.46
     VIH
    0.45
    Activations Density 0.187%

    No Known Activations