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

    Neuronpedia

    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. 20-GEMMASCOPE-RES-65K
    11. 47
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate uncertainty or vague locations

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

    references to locations or states of being

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

    somewhere, sometime, between

    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
    WireFormatLite
    -0.70
    IUrlHelper
    -0.69
    //
    -0.68
    numerusform
    -0.66
    HasAnnotation
    -0.65
    WriteBarrier
    -0.64
     "..\..\..\
    -0.64
     समीक्षक
    -0.63
     onCancelled
    -0.60
    ✨:
    -0.60
    POSITIVE LOGITS
    Somewhere
    0.92
     Somewhere
    0.79
     somewhere
    0.73
     between
    0.71
    somewhere
    0.70
    between
    0.69
     around
    0.60
    PRET
    0.60
    Else
    0.59
    enetrable
    0.58
    Activations Density 0.020%

    No Known Activations