© 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 - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10341
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or doubt regarding assistance and product fulfillment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endiri
    -0.47
     podr
    -0.47
    пуляр
    -0.45
    --
    -0.45
     Mondial
    -0.44
     årene
    -0.41
    Assuming
    -0.41
     pression
    -0.41
     declaratory
    -0.41
     acordo
    -0.41
    POSITIVE LOGITS
     unknownFields
    0.76
     Мексичка
    0.74
    WireFormatLite
    0.71
     kasarigan
    0.68
    featureID
    0.66
    GIVEREF
    0.64
    oa̍t
    0.61
    XmlAccessorType
    0.60
    MarshalTo
    0.60
     Chwiliwch
    0.60
    Activations Density 0.644%

    No Known Activations