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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4689
    Prev
    Next
    INDEX
    Explanations

    words that refer to high-frequency terms or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.80
    NOPQRST
    -0.78
    enderror
    -0.78
     ujednoznacz
    -0.76
    QMetaType
    -0.76
     arşivlendi
    -0.73
    脚注の使い方
    -0.71
    ništ
    -0.71
    migrationBuilder
    -0.70
     وتسجيلات
    -0.68
    POSITIVE LOGITS
    ll
    3.09
    LL
    2.20
     ll
    2.20
     LL
    1.76
    lll
    1.59
    Ll
    1.57
    lls
    1.47
     Ll
    1.38
    llll
    1.29
    llu
    1.20
    Activations Density 0.053%

    No Known Activations