© 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. 566
    Prev
    Next
    INDEX
    Explanations

    specific mentions of individuals, particularly in political contexts

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

    references to division or separating elements in a context

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

    Devin Nunes

    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
     Agamemnon
    -0.51
    DataURL
    -0.47
     pregunto
    -0.47
     impermeable
    -0.46
    azgo
    -0.46
    PageRoute
    -0.46
    amey
    -0.45
    encodeWith
    -0.45
    XHR
    -0.45
    excerpt
    -0.45
    POSITIVE LOGITS
    WireFormatLite
    0.89
    findpost
    0.68
    ConstraintMaker
    0.66
    makeConstraints
    0.61
    SequentialGroup
    0.60
     Identities
    0.59
    ंदीखरीदारी
    0.59
    WriteTagHelper
    0.56
    onomía
    0.55
     الرياضيه
    0.55
    Activations Density 0.008%

    No Known Activations