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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6732
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to convictions and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.76
    writeFieldEnd
    -0.76
     ویکی‌پدیا
    -0.69
     esternos
    -0.68
    titleMargin
    -0.65
     Cib
    -0.64
     Kwang
    -0.64
    horabuena
    -0.63
     Giz
    -0.63
    ^(@)
    -0.63
    POSITIVE LOGITS
     certific
    0.68
     cam
    0.63
     Kel
    0.62
     confirmation
    0.60
     confidence
    0.60
     Cam
    0.60
     conviction
    0.59
     confirmed
    0.59
     confirma
    0.58
     certificate
    0.58
    Activations Density 2.765%

    No Known Activations