© 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. 20-GEMMASCOPE-RES-16K
    11. 3477
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hesitation or negative responses

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

    Following "don't" or negation

    np_acts-logits-general · gemini-2.0-flash

    don't hesitate or forget

    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
    AndEndTag
    -0.58
     Appellants
    -0.55
    хьтан
    -0.54
    actualité
    -0.54
     gddr
    -0.52
     magnética
    -0.50
     outward
    -0.49
    Portale
    -0.49
     Petitioners
    -0.49
     appellants
    -0.49
    POSITIVE LOGITS
     hesitate
    1.22
     hesitated
    0.89
     hés
    0.83
     hesitant
    0.71
     hesit
    0.70
     hesitating
    0.70
     afraid
    0.68
     hesitation
    0.67
     too
    0.65
     shy
    0.63
    Activations Density 0.134%

    No Known Activations