© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 10064
    Prev
    Next
    INDEX
    Explanations

    information related to football players and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linebacker
    -0.42
     grosir
    -0.40
    Clearing
    -0.35
     clearing
    -0.35
     Clearing
    -0.34
     bezpieczeństwa
    -0.34
     sécur
    -0.33
    écu
    -0.33
    衛隊
    -0.32
     Sicherheits
    -0.32
    POSITIVE LOGITS
     forward
    0.84
     strikers
    0.82
     striker
    0.79
     attacking
    0.73
     forwards
    0.73
     attacker
    0.72
     attackers
    0.72
     delantero
    0.68
     atacante
    0.68
     wings
    0.66
    Activations Density 0.100%

    No Known Activations