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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8427
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ball."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iſt
    -0.78
    %")
    -0.72
    "]];
    -0.71
    %");
    -0.70
    })*/
    -0.69
     Eſ
    -0.65
     ainfi
    -0.65
    Rourke
    -0.64
     ======
    -0.64
    tuuri
    -0.62
    POSITIVE LOGITS
     balls
    1.10
    balls
    1.07
     Ball
    1.04
     Balls
    1.00
     BALL
    0.95
     Sk
    0.93
    Ball
    0.91
     ball
    0.89
     disks
    0.87
    ball
    0.82
    Activations Density 0.029%

    No Known Activations