© 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. 6154
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and phrases, particularly those concerning games and contests

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

    sports game results and statistics.

    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
    RTEX
    -0.53
     zijne
    -0.44
     silvestre
    -0.44
    GOTREF
    -0.44
    verick
    -0.44
     屋根
    -0.43
     organisme
    -0.42
     argint
    -0.42
     muestre
    -0.42
    amentul
    -0.41
    POSITIVE LOGITS
     game
    0.78
     games
    0.77
     match
    0.71
     matches
    0.71
     away
    0.68
     matchup
    0.65
     opener
    0.62
     road
    0.60
    games
    0.58
     rescheduled
    0.58
    Activations Density 0.170%

    No Known Activations