© 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. 7930
    Prev
    Next
    INDEX
    Explanations

    sports-related statistics and player achievements

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

    biographical information about athletes' international soccer career representations and debut details.

    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
    SequentialGroup
    -0.44
    muerzo
    -0.43
     musim
    -0.41
    iconCls
    -0.41
    Subviews
    -0.40
    routeProvider
    -0.40
     stadt
    -0.40
    イナー
    -0.39
    PreferredItem
    -0.39
     surabaya
    -0.39
    POSITIVE LOGITS
     national
    1.09
    national
    0.99
     сборной
    0.88
     seleção
    0.83
     nazionale
    0.77
     reprezenta
    0.77
     nationale
    0.75
     국가
    0.75
    国家
    0.75
     nation
    0.75
    Activations Density 0.157%

    No Known Activations