© 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. 8483
    Prev
    Next
    INDEX
    Explanations

    phrases indicating prominence or significance

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

    Following "most" or "more"

    np_acts-logits-general · gemini-2.0-flash

    most + adjective

    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
    TypedDataSet
    -0.73
    FormUrlEncoded
    -0.69
     فريبيس
    -0.68
     الرياضيه
    -0.65
     lebih
    -0.64
    very
    -0.63
    Autoritní
    -0.63
     noDo
    -0.62
    Very
    -0.61
    more
    -0.61
    POSITIVE LOGITS
     amount
    0.70
     photographed
    0.67
     searched
    0.64
    thest
    0.63
     talked
    0.63
     visited
    0.61
     coldest
    0.59
     purest
    0.58
     downloaded
    0.56
     simplest
    0.56
    Activations Density 0.074%

    No Known Activations