© 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. 3818
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions or feelings

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

    Word after pronoun or name

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by want or belief

    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
    клопе
    -0.70
     Parac
    -0.60
    becomes
    -0.59
    icose
    -0.59
     mxArray
    -0.57
     tended
    -0.56
    Creates
    -0.56
    Become
    -0.55
    ptid
    -0.54
     Werden
    -0.53
    POSITIVE LOGITS
    GEBURTSDATUM
    0.66
    ParallelGroup
    0.66
     épaules
    0.55
    UnitTesting
    0.55
     actually
    0.54
    RSpec
    0.53
    ModelAdmin
    0.53
     verke
    0.52
     genuinely
    0.51
     itulah
    0.50
    Activations Density 0.389%

    No Known Activations