© 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. 11-GEMMASCOPE-RES-16K
    11. 3880
    Prev
    Next
    INDEX
    Explanations

    contextual evidence and arguments in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doubtnut
    -0.68
    providedIn
    -0.66
     ویکی‌آمباردا
    -0.62
    IMPORTED
    -0.59
    ugian
    -0.58
     Wicidata
    -0.58
    PreferredItem
    -0.58
     كومونز
    -0.58
    Viitteet
    -0.57
    Климат
    -0.57
    POSITIVE LOGITS
     ویکی‌پدی
    0.53
    Джерела
    0.51
    むしろ
    0.46
     ostavi
    0.44
    ですよね
    0.43
    ;#
    0.42
     setShow
    0.41
    trina
    0.41
     udara
    0.41
     aveug
    0.41
    Activations Density 0.582%

    No Known Activations