© 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. 11836
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and specific identifiers

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

    Strings of two or three letters

    np_acts-logits-general · gemini-2.0-flash

    bernoulli or Inn

    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
    tas
    -0.79
    able
    -0.75
    e
    -0.73
    ا
    -0.72
    a
    -0.70
    tó
    -0.66
    the
    -0.63
    ae
    -0.60
    ability
    -0.59
    aus
    -0.59
    POSITIVE LOGITS
    nnnn
    0.60
    nnn
    0.59
     EnglishChoose
    0.57
    ̩
    0.56
     NDEBUG
    0.53
    ThroughAttribute
    0.53
    }{*}{}
    0.52
    AppRoutingModule
    0.52
     Yn
    0.51
    }{||
    0.51
    Activations Density 0.287%

    No Known Activations