© 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. 8301
    Prev
    Next
    INDEX
    Explanations

    elements related to feedback, suggestions, or contributions in a context that may refer to issues, problems, or improvements

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

    Letters followed by parentheses

    np_acts-logits-general · gemini-2.0-flash

    enumeration items starting with c

    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
    b
    -0.56
     C
    -0.50
     c
    -0.49
    c
    -0.49
    ض
    -0.48
      (
    -0.47
    CPtr
    -0.47
     Brandt
    -0.46
    bA
    -0.45
    C
    -0.45
    POSITIVE LOGITS
    __':
    0.56
    GEBURTSDATUM
    0.54
    Personensuche
    0.54
     Wikispecies
    0.53
     חיצוניים
    0.53
    wixt
    0.53
     famí
    0.52
    CreateModel
    0.52
    memoized
    0.52
    ыгана
    0.51
    Activations Density 0.107%

    No Known Activations