© 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. 11263
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal arguments and courtroom processes

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

    Preposition "by" followed by a gerund

    np_acts-logits-general · gemini-2.0-flash

    by followed by verb

    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
     domestiques
    -0.73
     ſon
    -0.71
     enfans
    -0.71
     greateſt
    -0.71
    Dragged
    -0.69
     sauvages
    -0.69
     démocr
    -0.68
     termica
    -0.68
     ſch
    -0.67
     scolaires
    -0.66
    POSITIVE LOGITS
     also
    0.82
     CreateTagHelper
    0.77
     actually
    0.72
     directly
    0.70
     quickly
    0.67
     finally
    0.66
     always
    0.66
     simply
    0.66
     effectively
    0.65
     not
    0.64
    Activations Density 0.465%

    No Known Activations