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. 20-GEMMASCOPE-RES-16K
    6. 10066
    Prev
    Next
    INDEX
    Explanations

    JavaScript code for handling state and rendering in a component

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.76
    CloseOperation
    -0.66
    :✨
    -0.64
    Дереккөздер
    -0.63
    principalColumn
    -0.63
     '\\;'
    -0.62
    脚注の使い方
    -0.62
     ་་
    -0.60
     Jefus
    -0.59
     createSlice
    -0.58
    POSITIVE LOGITS
     <
    0.91
     <>
    0.81
    <>
    0.79
    <
    0.71
    <tr>
    0.68
    (<
    0.55
    ={<
    0.55
    :<
    0.54
    ServletException
    0.53
    ><
    0.52
    Activations Density 0.024%

    No Known Activations