© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2087
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics and statistical data related to performance and demographics

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

    numerical data and statistical measurements in technical or scientific contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    statistical or quantitative data, particularly percentages, rates, measurements, and demographic figures.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    passages that present quantitative measurements or statistical figures—rates, percentages, totals, numeric descriptors, and other metrics across scientific, medical, geographic, financial, and demographic contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
    featureID
    -0.40
    DataSetChanged
    -0.40
     >=",
    -0.39
     &___
    -0.39
     defaultstate
    -0.38
    ísimas
    -0.36
    subpackage
    -0.34
     pieniądze
    -0.33
    mergeFrom
    -0.32
    ]<<"
    -0.32
    POSITIVE LOGITS
     amounted
    0.80
     beträgt
    0.75
     составляет
    0.75
     wynosi
    0.72
     состави
    0.71
     totaled
    0.68
     betrug
    0.65
     totalled
    0.62
     ranged
    0.62
     vaut
    0.62
    Activations Density 0.912%

    No Known Activations