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

    Neuronpedia

    APICircuit 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. 25-GEMMASCOPE-RES-16K
    6. 5947
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions

    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
    buttonBar
    -0.50
    зулта
    -0.49
    IndentedString
    -0.48
     rasa
    -0.46
     Gertrude
    -0.46
     Devine
    -0.45
     Dogg
    -0.45
    .•
    -0.44
    Distribuzione
    -0.43
    NTIS
    -0.43
    POSITIVE LOGITS
    ,[
    1.89
    .[
    1.75
    :[
    1.74
    $[
    1.69
     $[
    1.69
    ).[
    1.69
     ([
    1.67
    ([
    1.66
    /[
    1.64
    -[
    1.61
    Activations Density 2.211%

    No Known Activations