© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1601
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons and measurements

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

    measurement precision indicators like "to the nearest decimal" or "plus or minus" values in scientific or statistical data.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    numerical measurements and their precision values (including units like ±, cm, kg, and decimal points).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.90
    enderror
    -0.75
    contentLoaded
    -0.74
     resourceCulture
    -0.71
     autorytatywna
    -0.70
    Personensuche
    -0.69
    LookAnd
    -0.66
    참고
    -0.65
     Signalez
    -0.63
    Vidite
    -0.63
    POSITIVE LOGITS
     increments
    0.46
     slight
    0.44
     incremental
    0.39
     signifikan
    0.39
    ึ้น
    0.39
     mały
    0.38
     minor
    0.38
     slightly
    0.38
     dodatkowe
    0.37
     ganzen
    0.37
    Activations Density 0.700%

    No Known Activations