© 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. 22-GEMMASCOPE-RES-16K
    11. 12666
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authority or judgmental statements

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

    Statements or opinions attributed to people

    np_acts-logits-general · gemini-2.0-flash

    Councillor, Mr, Speaking, Bosses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.86
    ômico
    -0.80
     שוליים
    -0.79
    Cordialement
    -0.75
     חיצוניים
    -0.75
    contentLoaded
    -0.73
    SharedDtor
    -0.73
    tvguidetime
    -0.71
    Демографія
    -0.71
     lenker
    -0.70
    POSITIVE LOGITS
     bosses
    0.75
    Councillor
    0.66
    Speaking
    0.64
     Speaking
    0.63
    Descri
    0.61
    Organiser
    0.59
    READ
    0.59
     Picture
    0.59
    Mr
    0.57
     Councillor
    0.57
    Activations Density 0.048%

    No Known Activations