© 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. 30-GEMMASCOPE-RES-16K
    11. 9926
    Prev
    Next
    INDEX
    Explanations

    references to player trades and transactions in the context of sports

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

    Reconstitution of KcsA into lipid vesicles

    np_acts-logits-general · gemini-2.0-flash

    cards, trading cards

    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
    
    -0.42
     estekak
    -0.36
     romanzo
    -0.33
     noastre
    -0.31
     resourceCulture
    -0.29
     lavori
    -0.29
    Datuak
    -0.29
     vostri
    -0.28
     presentarse
    -0.28
     bénéficiaire
    -0.28
    POSITIVE LOGITS
     cards
    1.18
    cards
    1.02
     card
    1.01
     Cards
    1.01
    Cards
    0.92
     Card
    0.88
     trading
    0.86
     CARDS
    0.86
    card
    0.85
     collectors
    0.85
    Activations Density 0.163%

    No Known Activations