Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10642
    Prev
    Next
    INDEX
    Explanations

    system error messages and related codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    …………………………………………
    -0.75
     contemporaneous
    -0.69
    +:+
    -0.67
     Autorizaciones
    -0.65
     Shakspeare
    -0.65
     kasarigan
    -0.63
     circumstantial
    -0.62
     Independiente
    -0.62
    enseignements
    -0.61
     adenocarcinoma
    -0.60
    POSITIVE LOGITS
     =
    
    0.68
     redor
    0.60
     histó
    0.53
    vician
    0.53
    UseVisualStyle
    0.53
     sociali
    0.52
     odeur
    0.50
     organiza
    0.48
    uesia
    0.48
     <>",
    0.48
    Activations Density 0.914%

    No Known Activations