© 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. 38-GEMMASCOPE-RES-16K
    6. 6953
    Prev
    Next
    INDEX
    Explanations

    structured data and references in the text, particularly focusing on quotes, titles, and associated numeric or categorical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.84
    ViewFeatures
    -0.82
     idéia
    -0.78
     resourceCulture
    -0.77
     AssemblyCulture
    -0.76
     Wikiseite
    -0.75
     surla
    -0.74
    devamını
    -0.73
     Einfluß
    -0.68
     مشين
    -0.67
    POSITIVE LOGITS
     S
    0.44
     Hyundai
    0.41
     Samsung
    0.40
     K
    0.39
     Toyota
    0.39
     Honda
    0.39
     T
    0.38
     San
    0.38
     Nissan
    0.37
     Yamaha
    0.37
    Activations Density 4.464%

    No Known Activations