© 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. 2454
    Prev
    Next
    INDEX
    Explanations

    instances of a formal call to action or summons, particularly in a regal or official context

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

    today

    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
     précédente
    -0.58
    Geplaatst
    -0.55
     précédents
    -0.55
     vorigen
    -0.50
     pasada
    -0.50
     précédent
    -0.50
     previous
    -0.47
     précédentes
    -0.46
     veckor
    -0.45
     segi
    -0.45
    POSITIVE LOGITS
     today
    3.00
    today
    2.58
     Today
    2.56
    Today
    2.52
     tonight
    2.42
     todays
    2.22
     heute
    2.11
    Tonight
    2.10
     Tonight
    2.09
     TODAY
    2.05
    Activations Density 0.201%

    No Known Activations