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. 1-GEMMASCOPE-RES-16K
    6. 7255
    Prev
    Next
    INDEX
    Explanations

    terms related to professional soccer and player contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.84
    prefixer
    -0.74
     GenerationType
    -0.73
    PMailer
    -0.72
    ItemBackground
    -0.67
    verwijspagina
    -0.66
     InputDecoration
    -0.66
    thâu
    -0.66
    UnsafeEnabled
    -0.65
    FormTagHelper
    -0.65
    POSITIVE LOGITS
     '__
    0.57
     fú
    0.51
    stadium
    0.48
     stadion
    0.47
     friv
    0.46
     soccer
    0.46
     práctica
    0.46
    artik
    0.46
     Soccer
    0.46
    practice
    0.45
    Activations Density 0.389%

    No Known Activations