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. 3-GEMMASCOPE-RES-16K
    6. 9486
    Prev
    Next
    INDEX
    Explanations

    specifications related to CSS styles, particularly widths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apor
    -0.65
     pelle
    -0.63
    writeObject
    -0.59
    [/
    -0.59
    {/
    -0.57
     app
    -0.54
    TAS
    -0.54
    [@"
    -0.54
    <i>
    -0.54
    :\/\/
    -0.54
    POSITIVE LOGITS
    width
    2.77
     width
    2.60
    Width
    2.48
     Width
    2.48
    WIDTH
    2.42
     WIDTH
    2.29
     widths
    2.27
    widths
    1.78
     getWidth
    1.74
    宽度
    1.70
    Activations Density 0.043%

    No Known Activations