© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 2489
    Prev
    Next
    INDEX
    Explanations

    references to surveillance and monitoring practices

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

    the past

    np_acts-logits-general · gemini-2.0-flash

    past times and events

    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
     незавершена
    -0.61
    Искәрмәләр
    -0.59
    posedge
    -0.57
    CreateModel
    -0.57
    URLException
    -0.56
    %");
    -0.56
     herewith
    -0.55
     prochains
    -0.55
    今日は
    -0.53
    ValueStyle
    -0.53
    POSITIVE LOGITS
     back
    2.23
    back
    1.67
    Back
    1.67
     Back
    1.61
     years
    1.54
     decades
    1.48
     BACK
    1.45
    BACK
    1.36
     damals
    1.33
     vroeger
    1.31
    Activations Density 0.659%

    No Known Activations