© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9069
    Prev
    Next
    INDEX
    Explanations

    data related to community events and announcements

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

    Punctuation after a word

    np_acts-logits-general · gemini-2.0-flash

    end of code or sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ustainable
    -0.63
    seamnă
    -0.59
    anmoins
    -0.59
     malheureusement
    -0.58
     qPCR
    -0.58
     ambientales
    -0.58
    Ultimately
    -0.58
     incroy
    -0.58
     incentiv
    -0.57
     albeit
    -0.57
    POSITIVE LOGITS
     Mrs
    0.78
     Miss
    0.70
    Mrs
    0.66
    :—
    0.64
    Miss
    0.62
     Италијани
    0.61
     Misses
    0.60
     referenties
    0.60
    IntoConstraints
    0.59
    TagMode
    0.59
    Activations Density 0.205%

    No Known Activations