© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8491
    Prev
    Next
    INDEX
    Explanations

    technical terms and key phrases related to scientific methodologies and measurements

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

    Comes before references/citations

    np_acts-logits-general · gemini-2.0-flash

    academic citations, references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":
    -1.22
    "));
    -1.22
    )");
    -1.20
    >");
    -1.17
    ")));
    -1.16
    ")]
    -1.16
    '},
    -1.15
    "]);
    -1.13
    "):
    -1.11
    "))
    -1.09
    POSITIVE LOGITS
    <sup>
    2.04
    [
    1.83
     [
    1.61
    .[
    1.52
     ${
    1.51
    ,[
    1.43
    )[
    1.32
     $[
    1.25
    }[
    1.23
    ^{[
    1.18
    Activations Density 5.684%

    No Known Activations