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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 685
    Prev
    Next
    INDEX
    Explanations

    references to balls or ball-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.82
    EDEFAULT
    -0.69
    neté
    -0.65
     صوتيه
    -0.63
    ➟
    -0.58
    tification
    -0.57
     unil
    -0.56
     catholique
    -0.56
    wardship
    -0.55
     Tade
    -0.53
    POSITIVE LOGITS
     BALL
    0.99
     Ball
    0.93
     balls
    0.89
     ball
    0.88
    Ball
    0.85
    Balls
    0.82
     Balls
    0.80
    ball
    0.75
    BALL
    0.71
    istics
    0.69
    Activations Density 0.063%

    No Known Activations