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. 21-GEMMASCOPE-RES-16K
    6. 2753
    Prev
    Next
    INDEX
    Explanations

    scientific concepts and terms related to interactions at the atomic and molecular levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ")));
    
    -1.32
    )");
    
    -1.31
    ":
    
    -1.31
    '},
    
    -1.28
    "));
    
    -1.27
    "):
    
    -1.26
    .)}
    -1.24
    ")]
    
    -1.23
    "]);
    
    -1.21
    "))
    
    -1.19
    POSITIVE LOGITS
    <sup>
    2.14
    [
    1.82
     ${
    1.56
     [
    1.52
    .[
    1.32
    ${
    1.26
    ,[
    1.26
    ^{
    1.22
    $^{
    1.17
    )[
    1.16
    Activations Density 5.124%

    No Known Activations