© 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. 24-GEMMASCOPE-RES-16K
    11. 6021
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise, humor, or non-seriousness

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

    Interjections/exclamations

    np_acts-logits-general · gemini-2.0-flash

    exclamations and interjections

    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
     respectivamente
    -0.64
    AutoresizingMask
    -0.63
     respectively
    -0.62
     المعيارى
    -0.59
    respectively
    -0.54
     valamint
    -0.53
     suivante
    -0.51
    verständlich
    -0.51
     kautta
    -0.49
    nictwa
    -0.48
    POSITIVE LOGITS
     дописавши
    0.75
    !
    0.75
    ...
    0.71
    …
    0.71
    offsetof
    0.69
     thats
    0.66
    hh
    0.63
    !...
    0.60
     חיצוניים
    0.57
    dafx
    0.57
    Activations Density 0.136%

    No Known Activations