© 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 EvalsExportsinterp-engineNEWAPI 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. 3496
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "one" in various contexts

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

    one of

    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
    WebElementEntity
    -0.62
    OGND
    -0.57
     "..\..\
    -0.56
    ModelSerializer
    -0.56
     AssemblyCulture
    -0.55
    يكب
    -0.54
    клопе
    -0.54
    moveToFirst
    -0.52
     mato
    -0.52
     ['./
    -0.51
    POSITIVE LOGITS
     unique
    0.74
    unif
    0.58
     femininas
    0.58
     poveznice
    0.57
    unique
    0.57
    تفصیلات
    0.56
     einzigartigen
    0.55
     AssemblyTitle
    0.55
     ongles
    0.55
     einzig
    0.55
    Activations Density 0.042%

    No Known Activations