© 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. 24-GEMMASCOPE-RES-16K
    11. 3825
    Prev
    Next
    INDEX
    Explanations

    computer programming and data structures elements

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

    Abbreviations ending in "at" or "c"

    np_acts-logits-general · gemini-2.0-flash

    SQL category IDs

    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
    PhysRev
    -0.80
    脚注の使い方
    -0.74
    ########.
    -0.70
    KommentareTeilen
    -0.69
    bootstrapcdn
    -0.62
     useAppContext
    -0.60
     kasarigan
    -0.60
    Espèce
    -0.58
    AnimationsModule
    -0.58
    SYNOPSIS
    -0.57
    POSITIVE LOGITS
    enter
    0.63
    ustom
    0.57
    lick
    0.56
    lean
    0.55
    lear
    0.53
     enter
    0.52
    heck
    0.52
    entral
    0.52
    lose
    0.52
    reat
    0.51
    Activations Density 0.333%

    No Known Activations