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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29290
    Prev
    Next
    INDEX
    Explanations

    numeric values related to error codes and identifiers in a structured data format

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

    alphanumeric codes and identifiers

    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
    IUrlHelper
    -0.82
     <>",
    -0.82
    ]--;
    -0.77
    ISupport
    -0.77
     kasarigan
    -0.76
    ContentAsync
    -0.76
    ngdoc
    -0.75
    PropertyChanging
    -0.72
    tagext
    -0.72
    WebElementEntity
    -0.69
    POSITIVE LOGITS
     nargin
    0.52
    原始内容存档于
    0.50
     organisasi
    0.48
    waża
    0.47
    reactstrap
    0.46
    endfor
    0.45
    ranslated
    0.44
    mologie
    0.43
     oluşan
    0.43
     csomag
    0.43
    Activations Density 0.043%

    No Known Activations