© 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. 22-GEMMASCOPE-RES-16K
    11. 11681
    Prev
    Next
    INDEX
    Explanations

    statements about personal experiences and offerings

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

    Follows personal pronouns or "token"

    np_acts-logits-general · gemini-2.0-flash

    similarity, repetition, or continuation

    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
     дописавши
    -0.83
     étoient
    -0.81
     feroit
    -0.79
     avoient
    -0.77
     neceff
    -0.77
     auroit
    -0.75
     étoit
    -0.74
     fermés
    -0.74
     Majefty
    -0.73
     '\\;'
    -0.73
    POSITIVE LOGITS
     again
    0.73
     also
    0.73
    ditto
    0.67
    同上
    0.65
     likewise
    0.61
     idem
    0.59
    findpost
    0.58
     ALSO
    0.57
     similarly
    0.56
     infine
    0.54
    Activations Density 0.804%

    No Known Activations