© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 35349
    Prev
    Next
    INDEX
    Explanations

    numerical expressions, particularly those representing quantities or counts

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

    numbers followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ac
    -0.35
     treo
    -0.35
    FormsModule
    -0.35
     Stirn
    -0.34
    else
    -0.33
    uns
    -0.33
    ItemGroup
    -0.33
    ce
    -0.32
    up
    -0.32
    vin
    -0.32
    POSITIVE LOGITS
     BorderRadius
    0.60
    NameInMap
    0.56
     spéciaux
    0.55
    attutto
    0.54
    Datuak
    0.54
    الإنجليزية
    0.53
    ðsíða
    0.52
    linawan
    0.52
     メンテナ
    0.52
     tartalo
    0.52
    Activations Density 0.361%

    No Known Activations