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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11430
    Prev
    Next
    INDEX
    Explanations

    locations and events related to sports activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -0.52
     Normdatei
    -0.49
    internalType
    -0.49
    MLLoader
    -0.48
    providedIn
    -0.47
    Билгалдахарш
    -0.47
    出版年
    -0.47
    errHandler
    -0.46
     BytesLike
    -0.45
     StringTokenizer
    -0.45
    POSITIVE LOGITS
     stadium
    1.23
     Stadium
    1.12
     stadiums
    1.09
    stadium
    0.99
    Stadium
    0.95
     estadio
    0.93
     arenas
    0.91
     Estadio
    0.90
     arena
    0.88
     stadion
    0.86
    Activations Density 0.128%

    No Known Activations