© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 590
    Prev
    Next
    INDEX
    Explanations

    the presence of certain markers or tokens indicating the structure of text or data formats

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

    prepositions and temporal indicators related to events

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

    numerical/code sequences

    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
     July
    -0.89
     September
    -0.85
     October
    -0.85
     August
    -0.83
     June
    -0.82
     November
    -0.79
     April
    -0.78
    July
    -0.77
     February
    -0.77
     March
    -0.76
    POSITIVE LOGITS
    CloseOperation
    0.76
    InjectAttribute
    0.72
    sizeCache
    0.72
    mybatisplus
    0.70
    ValueStyle
    0.69
     bezeichneter
    0.68
    uxxxx
    0.67
     ***!
    0.67
    AccessorTable
    0.66
    yarnpkg
    0.63
    Activations Density 0.052%

    No Known Activations