© 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. 10862
    Prev
    Next
    INDEX
    Explanations

    points of view and arguments in favor of various perspectives

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

    Word that immediately follows: now, thought, gun, up, drive, country, body, there, line, there

    np_acts-logits-general · gemini-2.0-flash

    compound words and phrases

    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
    jectable
    -0.64
    tubers
    -0.62
    itisation
    -0.59
    migrationBuilder
    -0.58
    $_['
    -0.57
    swire
    -0.56
    ensed
    -0.55
    plevel
    -0.55
    GERS
    -0.54
    gings
    -0.54
    POSITIVE LOGITS
    neath
    1.38
    theless
    1.16
    ostante
    1.13
    currency
    1.13
    adays
    1.12
    teen
    1.07
    ward
    1.05
    stuffs
    1.02
    withstanding
    1.02
    while
    0.97
    Activations Density 0.484%

    No Known Activations