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. 3277
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS class attributes related to user interface elements

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

    HTML/Java class definitions

    np_acts-logits-general · gemini-2.0-flash

    HTML class and style uses

    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
     itſelf
    -0.83
    featureID
    -0.82
     ExecuteAsync
    -0.79
     myſelf
    -0.76
     Theſe
    -0.75
     ―――――
    -0.75
    rungsseite
    -0.73
     raiſ
    -0.72
     Shakspeare
    -0.71
     Anſ
    -0.71
    POSITIVE LOGITS
    Viitteet
    0.58
    defineProperty
    0.54
     lit
    0.50
    localVar
    0.48
    <eos>
    0.48
     ed
    0.47
    SuppressLint
    0.46
     key
    0.45
     localVar
    0.44
     B
    0.44
    Activations Density 0.054%

    No Known Activations