© 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. 15-GEMMASCOPE-RES-16K
    6. 2355
    Prev
    Next
    INDEX
    Explanations

    mathematical and statistical terminology related to probability distributions and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.46
    存于互联网档案馆
    -0.45
    Referensi
    -0.41
    chequer
    -0.40
    cadilly
    -0.38
    Referências
    -0.37
    VIAF
    -0.36
    InjectAttribute
    -0.36
     liable
    -0.35
     Duan
    -0.35
    POSITIVE LOGITS
    Попис
    0.50
     समीक्षाओं
    0.45
     PeEnEo
    0.43
    featureID
    0.42
     воло
    0.41
     INTERESAR
    0.39
    -------------</
    0.39
     metrów
    0.39
     nationaux
    0.38
     produse
    0.38
    Activations Density 1.270%

    No Known Activations