© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1310
    Prev
    Next
    INDEX
    Explanations

    terms related to academic or intellectual content

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

    ending in "s"

    np_acts-logits-general · gemini-2.0-flash

    intellect, dust, alcoholic, Festival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stalline
    -0.71
    ‌ای
    -0.70
     JpaRepository
    -0.68
    ‌ی
    -0.67
     Chwiliwch
    -0.67
    WriteLiteral
    -0.66
    く
    -0.66
    let
    -0.65
    дца
    -0.65
    agoza
    -0.65
    POSITIVE LOGITS
    s
    2.99
    ся
    1.23
    sted
    1.18
    ים
    1.16
    ы
    1.11
    ی
    1.11
    ات
    1.04
    sver
    1.04
    ۰۰
    0.99
    sly
    0.98
    Activations Density 1.141%

    No Known Activations