© 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. 270
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words "while" and "when."

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

    phrases related to jury deliberation or discussions

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

    actions happening while

    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
     знал
    -0.49
    Compos
    -0.47
     personnalisées
    -0.46
     cancellation
    -0.46
     bulunur
    -0.45
    それから
    -0.45
     fuga
    -0.45
    igshid
    -0.44
     annihilation
    -0.43
     trouxe
    -0.43
    POSITIVE LOGITS
     taking
    1.06
     doing
    1.01
     using
    1.00
     attempting
    1.00
     trying
    1.00
     working
    0.98
    InputBorder
    0.98
     looking
    0.93
     playing
    0.93
     making
    0.92
    Activations Density 0.094%

    No Known Activations