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. 16-GEMMASCOPE-RES-16K
    6. 185
    Prev
    Next
    INDEX
    Explanations

    values and metrics related to athletic performance

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

    Talk about athletic ability/skill

    np_acts-logits-general · gemini-2.0-flash

    physical ability and potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.69
     tiennent
    -0.63
    expandindo
    -0.63
    脚注の使い方
    -0.62
     Italijanski
    -0.62
    posób
    -0.61
    LocalizedString
    -0.61
    webElementGuid
    -0.59
    ustimmung
    -0.58
     Houſe
    -0.57
    POSITIVE LOGITS
    AddTagHelper
    0.58
     ***!
    0.55
     improved
    0.53
     mengembangkan
    0.52
     raw
    0.51
    MLLoader
    0.51
     developmental
    0.50
     mł
    0.49
     دیکھیے
    0.49
     maturing
    0.49
    Activations Density 0.145%

    No Known Activations