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. 13-GEMMASCOPE-RES-16K
    6. 6562
    Prev
    Next
    INDEX
    Explanations

    super constructor calls and initializations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aandacht
    -0.47
     algemene
    -0.47
     Arabian
    -0.45
     gql
    -0.44
    -0.44
    ggior
    -0.44
    emd
    -0.42
    #
    -0.42
     Yah
    -0.41
    férés
    -0.41
    POSITIVE LOGITS
    DoubleQuotes
    0.81
     nahilalakip
    0.75
    ":"",
    0.75
    Bibliograf
    0.72
    Cyfeiriadau
    0.72
     mapStateToProps
    0.71
    HtmlAttribute
    0.71
    Становништво
    0.68
    曖昧さ回避
    0.68
    InlineData
    0.67
    Activations Density 0.027%

    No Known Activations