© 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. 7-GEMMASCOPE-RES-16K
    6. 11062
    Prev
    Next
    INDEX
    Explanations

    actions and attributes related to performance in competitive sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     boucles
    -0.48
    нулась
    -0.45
     famí
    -0.45
     panneau
    -0.43
    ắp
    -0.43
     måde
    -0.43
    Nights
    -0.42
    way
    -0.42
    йдите
    -0.42
    valo
    -0.42
    POSITIVE LOGITS
    __':
    
    0.68
    ])):
    0.65
    ErrUnexpectedEOF
    0.65
    makeConstraints
    0.62
    "]));
    0.62
    ')],
    0.62
    }}],
    0.62
     rugby
    0.62
     ...]
    0.60
    ("}");
    0.60
    Activations Density 0.166%

    No Known Activations