© 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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5339
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and standings related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     man
    -0.46
    land
    -0.46
    mat
    -0.45
     Glied
    -0.42
     genitori
    -0.42
    Th
    -0.42
     jenis
    -0.39
    arjo
    -0.38
     Th
    -0.38
    sold
    -0.38
    POSITIVE LOGITS
     '\\;'
    1.11
    IsMutable
    1.08
     مرئيه
    1.05
    aarrggbb
    0.92
    ientôt
    0.79
    TagMode
    0.78
    WithIOException
    0.77
    EDEFAULT
    0.75
     насељу
    0.73
    Референце
    0.70
    Activations Density 0.093%

    No Known Activations