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. 22-GEMMASCOPE-RES-16K
    6. 6035
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and data analysis

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

    Tokens preceding citations/references

    np_acts-logits-general · gemini-2.0-flash

    scientific and research terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )");
    
    -1.24
    ":
    
    -1.21
    ")));
    
    -1.20
    ")]
    
    -1.19
    .)}
    -1.18
    "):
    
    -1.17
    "));
    
    -1.16
    '},
    
    -1.16
    "]);
    
    -1.13
    "))
    
    -1.11
    POSITIVE LOGITS
    <sup>
    2.20
     ${
    1.73
    [
    1.64
    ${
    1.36
     [
    1.35
    ^{
    1.29
    $^{
    1.25
    ¹
    1.21
     $^{
    1.20
    ^[
    1.12
    Activations Density 4.553%

    No Known Activations