© 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 EvalsExportsAPI 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. 3607
    Prev
    Next
    INDEX
    Explanations

    code references and object manipulation patterns in scripts

    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
    gestone
    -0.57
    eway
    -0.53
     "/";
    -0.53
    (":");
    -0.52
     GenerationType
    -0.51
     τό
    -0.49
    __))
    -0.49
    Hentet
    -0.48
    )"),
    -0.47
    uitable
    -0.47
    POSITIVE LOGITS
     Paglinawan
    0.62
     quæ
    0.57
    \{\\
    0.56
     кӀ
    0.54
     africana
    0.54
     fjor
    0.53
    RTDA
    0.53
    MenuGroup
    0.52
     Савезне
    0.51
    HtmlAttribute
    0.51
    Activations Density 1.087%

    No Known Activations