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. 16-GEMMASCOPE-RES-65K
    6. 53223
    Prev
    Next
    INDEX
    Explanations

    references to plant health, particularly regarding pests and remedial actions

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

    in addition, was present, das::, issued in

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     invokingState
    -0.75
    UnknownFields
    -0.75
    oredCriteria
    -0.73
    omitempty
    -0.72
     '\\;'
    -0.72
     שוליים
    -0.71
    dymyr
    -0.69
    脚注の使い方
    -0.68
    DrawerToggle
    -0.67
    aarrggbb
    -0.67
    POSITIVE LOGITS
    season
    0.63
     season
    0.63
     garden
    0.59
     seasonal
    0.59
     winter
    0.58
     SEASON
    0.54
     summer
    0.50
     saisons
    0.50
     сезон
    0.50
    Seasonal
    0.50
    Activations Density 0.068%

    No Known Activations