© 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. 23-GEMMASCOPE-RES-16K
    6. 5207
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports actions and mechanics, particularly focusing on basketball and volleyball

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.54
    stretch
    -0.53
     mergeFrom
    -0.53
    ghen
    -0.52
    newtheorem
    -0.52
    INGE
    -0.52
     utafitiHapana
    -0.52
    helves
    -0.50
    hydra
    -0.49
     CreateTagHelper
    -0.49
    POSITIVE LOGITS
     ball
    2.29
    ball
    1.90
     Ball
    1.74
     balls
    1.74
    Ball
    1.72
     BALL
    1.67
    BALL
    1.59
    balls
    1.53
     Balls
    1.41
     balón
    1.36
    Activations Density 0.191%

    No Known Activations