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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1150
    Prev
    Next
    INDEX
    Explanations

    terms related to visual representation and aesthetics

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

    terms related to visual aesthetics and styles

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

    visual examination, representation, style, or Studio

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Abp
    -0.48
     ramos
    -0.48
     Westfield
    -0.47
     nisi
    -0.46
    гда
    -0.46
     useRouter
    -0.45
    EndInit
    -0.45
    raborty
    -0.44
    wide
    -0.43
    laag
    -0.43
    POSITIVE LOGITS
     utafitiHapana
    0.79
     cues
    0.72
    isations
    0.69
     aids
    0.68
    pyplot
    0.66
    spatial
    0.65
    Politik
    0.65
     appeal
    0.64
    VISUAL
    0.63
     insuffisamment
    0.63
    Activations Density 0.017%

    No Known Activations