© 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. 10635
    Prev
    Next
    INDEX
    Explanations

    phrases describing the evaluation and perception of authority and social structures

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

    Follows a verb "as" defining a concept

    np_acts-logits-general · gemini-2.0-flash

    described as, defined as, interpreted as

    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
     chi̍t
    -0.58
     Meksiku
    -0.57
    emples
    -0.50
    endio
    -0.47
     Beweis
    -0.46
     selected
    -0.46
    orteur
    -0.46
     As
    -0.45
     chỗ
    -0.44
    zib
    -0.43
    POSITIVE LOGITS
     differently
    1.30
     favorably
    0.81
     autrement
    0.80
     negatively
    0.77
     incorrectly
    0.77
     simply
    0.77
     similarly
    0.77
     autorytatywna
    0.76
     fondly
    0.75
     favourably
    0.73
    Activations Density 0.436%

    No Known Activations