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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16359
    Prev
    Next
    INDEX
    Explanations

    phrases signaling legal or formal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cyfeiriadau
    -0.70
     kasarigan
    -0.70
    endphp
    -0.69
    OGND
    -0.69
     otomatig
    -0.68
    QMetaType
    -0.68
     Infórmanos
    -0.64
     <>",
    -0.64
     linkovi
    -0.64
     Wikimedijinoj
    -0.63
    POSITIVE LOGITS
     obstante
    0.52
     entanto
    0.39
     however
    0.35
    uttavia
    0.35
    彼は
    0.35
     autem
    0.35
    anmoins
    0.34
    彼女は
    0.34
     infatti
    0.33
    而言
    0.32
    Activations Density 0.634%

    No Known Activations