Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 11043
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performance, specifically actions and statistics in a game context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    리를
    -0.44
    τούν
    -0.41
     anti
    -0.38
     degli
    -0.38
    <eos>
    -0.36
     compagn
    -0.36
     a
    -0.35
     ][
    -0.35
     [
    -0.35
    Resizable
    -0.34
    POSITIVE LOGITS
    ChildScrollView
    1.01
    Personensuche
    0.95
    ंदीखरीदारी
    0.91
    ValueStyle
    0.89
    AnimationsModule
    0.84
    Спасылкі
    0.81
    RegressionTest
    0.80
    InputBorder
    0.80
     wireType
    0.80
    (!__
    0.80
    Activations Density 0.370%

    No Known Activations