© 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. 1480
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to programming or computer architecture

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

    terms related to memory management and program execution in computing

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

    hardware memory access

    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
     ujednoznacz
    -0.70
    !*\
    -0.69
    onViewCreated
    -0.68
     يتيمه
    -0.67
     ProtoMessage
    -0.67
     مرئيه
    -0.65
    ANTLR
    -0.64
    ็จ
    -0.64
    CrossRef
    -0.63
     typelib
    -0.62
    POSITIVE LOGITS
    UrlResolution
    0.60
    rrggbb
    0.54
    pylab
    0.46
    ocell
    0.45
    PathParam
    0.43
     registre
    0.43
     dictadura
    0.42
     regist
    0.42
    pyplot
    0.42
     tslint
    0.42
    Activations Density 0.146%

    No Known Activations