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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 15655
    Prev
    Next
    INDEX
    Explanations

    references to tennis tournaments and player performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.56
    zuführen
    -0.52
    {{/
    -0.51
    protoimpl
    -0.51
    ichio
    -0.50
     kasarigan
    -0.48
     circ
    -0.48
    ונות
    -0.47
    norr
    -0.47
    !*\
    -0.45
    POSITIVE LOGITS
     tennis
    1.34
     Tennis
    1.25
    Tennis
    1.15
    tennis
    1.13
     tenis
    1.00
     Tenis
    0.97
     Badminton
    0.95
     badminton
    0.94
    minton
    0.92
    ENNIS
    0.91
    Activations Density 0.136%

    No Known Activations