© 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. 6441
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating a lack of certainty

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

    Follows the word "not"

    np_acts-logits-general · gemini-2.0-flash

    not followed by qualifier

    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
    -0.82
    AutoScaleMode
    -0.72
    TestBed
    -0.72
     Vikipedi
    -0.69
    enderror
    -0.66
     بيها
    -0.65
    RenderAtEndOf
    -0.62
    setVerticalGroup
    -0.62
     ModelExpression
    -0.61
    GEBURTSDATUM
    -0.61
    POSITIVE LOGITS
     fair
    0.76
     uncommon
    0.72
     news
    0.60
     relevant
    0.59
     unusual
    0.57
     sustainable
    0.57
     realistic
    0.55
     surprising
    0.55
     intended
    0.54
     appropriate
    0.53
    Activations Density 0.235%

    No Known Activations