© 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. 12-GEMMASCOPE-RES-16K
    6. 2403
    Prev
    Next
    INDEX
    Explanations

    references to sample preparation and characteristics in experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     electricidad
    -0.64
     segredo
    -0.61
     direta
    -0.59
     financeira
    -0.57
     elétrica
    -0.54
     computadoras
    -0.54
     inalámb
    -0.53
     finanzas
    -0.52
     vermelha
    -0.52
     inalámbrica
    -0.52
    POSITIVE LOGITS
     sample
    1.68
     Sample
    1.63
    Sample
    1.53
    sample
    1.51
     SAMPLE
    1.50
    SAMPLE
    1.45
     Samples
    1.43
     samples
    1.41
    Samples
    1.29
     SAMPLES
    1.20
    Activations Density 0.147%

    No Known Activations