© 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. 8591
    Prev
    Next
    INDEX
    Explanations

    segments in the text that signify the start of a significant new section or topic

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

    Follows "an" or "An"

    np_acts-logits-general · gemini-2.0-flash

    starts sentences with articles and numbers

    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
    ratulations
    -0.79
    })$}
    -0.74
    gnition
    -0.72
    "):
    -0.72
    "])
    -0.65
    %\]
    -0.65
    '];?>
    -0.65
    "]);
    -0.64
     few
    -0.64
    ineſs
    -0.64
    POSITIVE LOGITS
    Geplaatst
    0.73
    Jeografia
    0.64
     AssemblyProduct
    0.63
     ivelany
    0.58
     onCancelled
    0.57
    D
    0.53
    X
    0.52
    writeFieldEnd
    0.51
     submarines
    0.51
    IntoConstraints
    0.50
    Activations Density 0.077%

    No Known Activations