© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7974
    Prev
    Next
    INDEX
    Explanations

    references to technology, particularly in the context of information technology and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clínico
    -0.39
    myModal
    -0.30
     Zust
    -0.30
    Organisateur
    -0.29
     Nacionales
    -0.28
     colonias
    -0.28
    queles
    -0.28
    haften
    -0.28
     Erkenntnis
    -0.28
    hafte
    -0.27
    POSITIVE LOGITS
    nological
    0.80
     advancement
    0.71
    nologi
    0.71
     advancements
    0.69
    providedIn
    0.68
     faſt
    0.67
    Vidite
    0.66
    nolog
    0.65
     itſelf
    0.64
     innovation
    0.63
    Activations Density 0.073%

    No Known Activations