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. 5-GEMMASCOPE-RES-16K
    6. 4723
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting elements and environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.83
    WarningLevel
    -0.74
     referenties
    -0.65
     lenker
    -0.64
    FormBorderStyle
    -0.63
    picasso
    -0.59
    GraphicsUnit
    -0.59
    Puss
    -0.58
    adaptiveStyles
    -0.57
    JspWriter
    -0.56
    POSITIVE LOGITS
     дописавши
    0.85
    {
    0.82
    mtable
    0.81
    {
    
    0.71
    {(
    0.67
    {[
    0.66
    (!__
    0.64
     brief
    0.64
    <bos>
    0.63
     CreateTagHelper
    0.62
    Activations Density 0.066%

    No Known Activations