© 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. 30-GEMMASCOPE-RES-16K
    6. 12517
    Prev
    Next
    INDEX
    Explanations

    references to achievements in sports and competition results

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

    Finishing positions in competitions

    np_acts-logits-general · gemini-2.0-flash

    athlete rankings and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Literatuur
    -0.45
    Personendaten
    -0.36
     Réponses
    -0.36
    AppMethodBeat
    -0.34
    Kanpo
    -0.34
     pacote
    -0.32
     nowrap
    -0.31
     pro
    -0.31
     lateinit
    -0.30
     institution
    -0.30
    POSITIVE LOGITS
     finish
    1.07
     finishing
    1.05
     placing
    0.96
     finishes
    0.95
     runner
    0.94
    finishing
    0.94
    Finishing
    0.92
     Finishing
    0.90
     Placing
    0.90
     finisher
    0.90
    Activations Density 0.144%

    No Known Activations