© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13825
    Prev
    Next
    INDEX
    Explanations

    instances of notable athletic performances or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Word(s) after team names

    np_acts-logits-general · gemini-2.0-flash

    sports teams followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.98
     imaginable
    -0.63
     {*}
    -0.60
     EconPapers
    -0.60
     precedent
    -0.58
    habitude
    -0.58
     Actualmente
    -0.57
    principalColumn
    -0.57
     lately
    -0.57
    bosis
    -0.55
    POSITIVE LOGITS
     betweenstory
    0.62
    ConverterFactory
    0.57
    Boxscore
    0.57
     estimés
    0.52
     تضيفلها
    0.49
    ngdoc
    0.47
     poch
    0.47
    ModelSerializer
    0.47
    createCanvas
    0.46
    outcome
    0.45
    Activations Density 0.096%

    No Known Activations