© 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. 10127
    Prev
    Next
    INDEX
    Explanations

    terms and conditions related to legal agreements and probation

    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
    />";
    -0.60
     disponibilités
    -0.59
    ]';
    -0.48
    хва
    -0.47
    ])));
    -0.46
    `<
    -0.45
    ()};
    -0.44
     http
    -0.43
    ()");
    -0.43
    ++){
    -0.43
    POSITIVE LOGITS
    mybatisplus
    0.99
    UnusedPrivate
    0.78
     EconPapers
    0.78
    ftagPool
    0.74
     autorytatywna
    0.74
    الحياه
    0.66
    rungsseite
    0.64
     cdti
    0.63
    المشاركات
    0.63
     resourceCulture
    0.61
    Activations Density 0.818%

    No Known Activations