© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1137
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, primarily periods and parentheses

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

    Punctuation followed by capitalized word

    np_acts-logits-general · gemini-2.0-flash

    ).)

    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
    UrlResolution
    -1.13
    ̯
    -0.65
    TagHelpers
    -0.59
    érience
    -0.59
    dehyde
    -0.55
    ItemModel
    -0.55
    LEncoder
    -0.55
    audrait
    -0.52
    ggiamento
    -0.51
    SourceChecksum
    -0.50
    POSITIVE LOGITS
     Monfieur
    0.79
     Also
    0.70
    ).)
    0.70
     isolato
    0.69
    তথ্যসূত্র
    0.69
     Efq
    0.69
     nakalista
    0.68
     scolas
    0.67
    )."
    0.67
     émotions
    0.67
    Activations Density 0.233%

    No Known Activations