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. 25-GEMMASCOPE-RES-16K
    6. 12585
    Prev
    Next
    INDEX
    Explanations

    references to sports leagues and competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zensionen
    -0.54
    AddTagHelper
    -0.51
    TagHelpers
    -0.49
    yarnpkg
    -0.49
    CPtr
    -0.48
    parsedMessage
    -0.47
     Procu
    -0.46
    mazon
    -0.46
     familiari
    -0.45
    IconModule
    -0.45
    POSITIVE LOGITS
     organisers
    0.76
     tournaments
    0.75
     sanction
    0.73
    Clubs
    0.70
     conferences
    0.70
     format
    0.69
     organiser
    0.69
     organizers
    0.68
     clubs
    0.68
     staging
    0.67
    Activations Density 0.253%

    No Known Activations