© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10553
    Prev
    Next
    INDEX
    Explanations

    statements of authority and personal conviction

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

    "accept" or "move on"

    np_acts-logits-general · gemini-2.0-flash

    accepting and moving on

    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
     Normdatei
    -0.64
     мәкал
    -0.63
     hés
    -0.62
     تانيه
    -0.61
     duos
    -0.57
    utnik
    -0.56
     esboço
    -0.56
     myſelf
    -0.55
    DataAnnotations
    -0.54
     guineas
    -0.53
    POSITIVE LOGITS
     accept
    1.75
     acceptance
    1.67
     accepting
    1.64
     Accept
    1.58
     accepts
    1.57
    accept
    1.55
     Accepting
    1.53
     ACCEPT
    1.52
     accepted
    1.51
     Acceptance
    1.50
    Activations Density 0.302%

    No Known Activations