© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14857
    Prev
    Next
    INDEX
    Explanations

    words expressing strong opinions or calls to action

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

    Imperative verbs following "to"

    np_acts-logits-general · gemini-2.0-flash

    stop or shut

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ">//
    -0.69
    koli
    -0.54
     marty
    -0.52
     föruts
    -0.51
    openSession
    -0.50
    త్ర
    -0.50
     trygg
    -0.47
     bestens
    -0.46
     algod
    -0.45
     möjlighet
    -0.45
    POSITIVE LOGITS
     stop
    1.48
     Stop
    1.36
    Stop
    1.34
     shut
    1.34
    stop
    1.28
    Shut
    1.22
     STOP
    1.21
     Shut
    1.20
    shut
    1.19
     SHUT
    1.13
    Activations Density 0.274%

    No Known Activations