Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3036
    Prev
    Next
    INDEX
    Explanations

    the word "ball" in various contexts related to sports or games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     broadway
    -0.67
    helves
    -0.65
     Myra
    -0.60
     Drexel
    -0.59
    ன்ப
    -0.59
     Archipelago
    -0.59
    ]';
    -0.57
     compri
    -0.54
     Debe
    -0.54
     Prieto
    -0.52
    POSITIVE LOGITS
     ball
    3.38
     Ball
    3.03
    ball
    2.93
     balls
    2.93
     BALL
    2.89
    Ball
    2.82
     Balls
    2.62
    BALL
    2.59
    balls
    2.57
    Balls
    2.35
    Activations Density 0.034%

    No Known Activations