© 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. 7233
    Prev
    Next
    INDEX
    Explanations

    terms related to combat sports and actions performed during fights

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

    Characters or symbols in structured data

    np_acts-logits-general · gemini-2.0-flash

    articles followed by other words

    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
    FirstResponder
    -0.59
     مرئيه
    -0.51
    Unisex
    -0.50
     вс
    -0.49
    rachtet
    -0.48
     незавершена
    -0.47
    ppro
    -0.46
    Germain
    -0.46
    streifen
    -0.46
    ThroughAttribute
    -0.46
    POSITIVE LOGITS
     légales
    0.58
    oredCriteria
    0.55
    новниш
    0.51
     DDT
    0.51
    Backdrop
    0.50
     <>",
    0.48
    发表于
    0.48
    ensement
    0.48
    processable
    0.47
     suicide
    0.47
    Activations Density 0.112%

    No Known Activations