© 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. 4032
    Prev
    Next
    INDEX
    Explanations

    negative contractions and forms of negation in sentences

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

    Contractions ending in "t" or "'t"

    np_acts-logits-general · gemini-2.0-flash

    contractions ending in n't

    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
     lenker
    -0.83
    IsMutable
    -0.83
    ftagPool
    -0.81
    transQ
    -0.80
    Quali
    -0.80
    PropertyChanging
    -0.79
    WebServlet
    -0.79
    sterious
    -0.78
    Pratique
    -0.75
     CURIAM
    -0.73
    POSITIVE LOGITS
    t
    0.52
     t
    0.51
    lt
    0.47
     ţ
    0.47
    T
    0.47
    ’
    0.46
    0.44
    ot
    0.44
    end
    0.44
    dt
    0.42
    Activations Density 0.061%

    No Known Activations