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. 6238
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data or metadata, especially in a programming or JSON context

    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
    •JSON Features

    No Comments

    Negative Logits
     snippetHide
    -1.50
    IntoConstraints
    -1.37
     Мексичка
    -1.29
    GraphicsUnit
    -1.27
     pinulongan
    -1.26
    AndEndTag
    -1.25
    principalColumn
    -1.25
    expandindo
    -1.24
     nahilalakip
    -1.24
    CloseOperation
    -1.19
    POSITIVE LOGITS
    ma
    0.50
    op
    0.48
    val
    0.48
    z
    0.45
    off
    0.45
    ore
    0.44
    k
    0.44
    f
    0.44
    me
    0.43
    us
    0.43
    Activations Density 1.165%

    No Known Activations