© 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. 10964
    Prev
    Next
    INDEX
    Explanations

    formatting elements and symbols commonly used in coding and documentation

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

    Text within brackets and citations

    np_acts-logits-general · gemini-2.0-flash

    citation markers and structures

    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
    (
    -0.81
    ,
    -0.70
    {
    -0.60
     TestBed
    -0.58
    -0.54
    .
    -0.54
    /
    -0.53
    [
    -0.53
    \
    -0.53
    $
    -0.52
    POSITIVE LOGITS
     $]$
    0.77
     MainAxisSize
    0.66
    [][]
    0.65
    _]
    0.64
    PrototypeOf
    0.63
    atici
    0.63
     inconvénients
    0.62
    ]>
    0.62
    _[
    0.62
    θεν
    0.61
    Activations Density 0.577%
    No Known Activations