© 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. 7729
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions related to cancer and tumor types

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

    medical research terminology related to cancer and biological processes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    scientific and medical terminology, particularly disease names, drug compounds, cell types, and technical abbreviations.

    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
    GEBURTSDATUM
    -0.42
     تعدى
    -0.41
    reportWebVitals
    -0.41
     Parcelable
    -0.38
    EDEFAULT
    -0.35
    writerow
    -0.33
    HtmlAttribute
    -0.33
    Билгалдахарш
    -0.33
    SerializedName
    -0.32
     soprav
    -0.32
    POSITIVE LOGITS
     model
    0.76
     models
    0.71
     cultured
    0.69
     modèle
    0.69
     модель
    0.68
     human
    0.67
     modelu
    0.66
     modelo
    0.66
     mice
    0.65
     murine
    0.65
    Activations Density 2.719%

    No Known Activations