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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5856
    Prev
    Next
    INDEX
    Explanations

    comments or annotations in code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.81
     zoude
    -0.81
    adeloupe
    -0.78
    genodigd
    -0.77
    mpagne
    -0.76
    UserScript
    -0.76
     stiefe
    -0.75
     laſſen
    -0.74
     ब्रेकडाउन
    -0.73
     للمعارف
    -0.72
    POSITIVE LOGITS
    //
    0.91
    ///
    0.91
     *
    0.86
    *
    0.81
    //
    0.64
    [toxicity=0]
    0.64
     //
    0.63
    #
    0.56
     
    0.55
    +//
    0.55
    Activations Density 0.092%

    No Known Activations