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. 20-GEMMASCOPE-RES-16K
    6. 9410
    Prev
    Next
    INDEX
    Explanations

    elements related to configurations and options in code structures

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

    Code or programmatic keywords

    np_acts-logits-general · gemini-2.0-flash

    programming syntax

    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
    rungsseite
    -0.71
    Datuak
    -0.70
     препратки
    -0.63
     ReactDOM
    -0.59
    Tracce
    -0.58
    hyrchwyd
    -0.56
     дописавши
    -0.53
    Bronnen
    -0.52
     >=",
    -0.52
    cjon
    -0.52
    POSITIVE LOGITS
    [
    1.05
     [
    0.94
    _[
    0.93
    '][
    0.90
    "][
    0.87
    __[
    0.82
    $[
    0.81
     $[
    0.79
    ][
    0.77
    )[
    0.74
    Activations Density 0.107%

    No Known Activations