© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5757
    Prev
    Next
    INDEX
    Explanations

    quantities and numerical references in the text

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

    Numbers indicating a quantity or duration

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     épaules
    -0.40
     okolí
    -0.31
     Handeln
    -0.31
     względem
    -0.31
     werking
    -0.31
    ("]");
    -0.30
     hasilnya
    -0.30
     rutina
    -0.29
     lèvres
    -0.29
     rozhod
    -0.28
    POSITIVE LOGITS
    таратура
    0.71
     different
    0.68
     dialects
    0.68
     EconPapers
    0.66
     successive
    0.65
    rungsseite
    0.63
     beſch
    0.61
    RTLU
    0.61
     verſch
    0.61
    AddTagHelper
    0.60
    Activations Density 0.498%

    No Known Activations