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. 1047
    Prev
    Next
    INDEX
    Explanations

    references to historical buildings and architecture

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

    historical references to architectural features and structures

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

    dating, dates, dated

    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
    PRNewswire
    -0.69
    NameInMap
    -0.64
    KommentareTeilen
    -0.61
    WriteTagHelper
    -0.53
    LookAnd
    -0.53
     JMenuItem
    -0.50
     beginnetje
    -0.49
    +:+
    -0.47
     الحره
    -0.45
    toBeTruthy
    -0.45
    POSITIVE LOGITS
     surviving
    1.19
     survives
    1.08
     extant
    1.07
     survive
    1.07
     earliest
    1.02
     preserved
    0.97
     dating
    0.96
     survived
    0.95
    Surviving
    0.93
     dated
    0.93
    Activations Density 0.228%

    No Known Activations