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. 6780
    Prev
    Next
    INDEX
    Explanations

    parentheses or closing punctuation marks

    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
     pleaſure
    -0.86
    ſhip
    -0.71
     houſe
    -0.70
    %;">
    -0.70
    ="/">
    -0.68
    {}/
    -0.67
    ;">
    
    -0.67
     poffe
    -0.67
    "){
    
    -0.65
    !")
    
    -0.65
    POSITIVE LOGITS
    expandindo
    0.64
     AssemblyCulture
    0.60
     kasarigan
    0.55
    U
    0.55
     mobilier
    0.54
    IUrlHelper
    0.53
    MethodInfo
    0.53
    ंदीखरीदारी
    0.52
    دانشنامهٔ
    0.51
    setcounter
    0.50
    Activations Density 0.910%

    No Known Activations