© 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. 33-GEMMASCOPE-RES-16K
    6. 10737
    Prev
    Next
    INDEX
    Explanations

    football-related terms and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.69
     HasFactory
    -0.65
    Offensive
    -0.63
     StatefulWidget
    -0.63
     Offensive
    -0.63
    routeProvider
    -0.62
     offensive
    -0.61
     Autorisations
    -0.59
    OGND
    -0.58
     Autorizaciones
    -0.58
    POSITIVE LOGITS
     sack
    0.46
     linebacker
    0.44
     Defensive
    0.42
     sacks
    0.40
     defensive
    0.40
     safety
    0.38
     edge
    0.38
    Defensive
    0.36
     corner
    0.35
     outside
    0.35
    Activations Density 0.095%

    No Known Activations