© 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. 4766
    Prev
    Next
    INDEX
    Explanations

    numerical data and specific statistics related to sports events

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

    references to numerical statistics and game results in sports writing.

    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
     Numerade
    -0.60
    +#+
    -0.53
     utafitiHapana
    -0.46
    Искәрмәләр
    -0.44
     nonUne
    -0.42
     Мексичка
    -0.39
     betweenstory
    -0.37
    ppuden
    -0.37
    httphttps
    -0.35
    heure
    -0.35
    POSITIVE LOGITS
     base
    0.92
     bases
    0.85
     third
    0.79
     Bases
    0.78
    base
    0.77
     Base
    0.77
    bases
    0.75
     Third
    0.75
     second
    0.73
    Third
    0.72
    Activations Density 0.076%

    No Known Activations