© 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. 3614
    Prev
    Next
    INDEX
    Explanations

    terms related to academic institutions and their qualities, particularly in the context of research

    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
    assium
    -0.81
    WindowConstants
    -0.76
    estinal
    -0.73
    Σε
    -0.67
    estris
    -0.66
    ulele
    -0.65
    ifrance
    -0.65
    [^
    -0.63
    modb
    -0.62
    твра
    -0.61
    POSITIVE LOGITS
     of
    1.76
    Portail
    0.97
    ]%
    0.87
    fillType
    0.86
     của
    0.85
     behulp
    0.82
     των
    0.82
    ของ
    0.81
    Beware
    0.80
    agisse
    0.77
    Activations Density 1.284%

    No Known Activations