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. 13-GEMMASCOPE-RES-16K
    6. 50
    Prev
    Next
    INDEX
    Explanations

    patterns related to HTML tags and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    seems to attend between HTML/code tokens, likely looking for structural relationships in markup or code snippets.

    oai_attention-head · claude-3-5-haiku-20241022Triggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.67
     Мексичка
    -0.60
    endphp
    -0.60
    LookAnd
    -0.58
    TagMode
    -0.56
     beginnetje
    -0.55
    ClientSize
    -0.53
    InitVars
    -0.52
     Arhi
    -0.51
    IsInitialized
    -0.51
    POSITIVE LOGITS
    expandindo
    0.69
    writerow
    0.65
     ↑
    0.62
    ipedi
    0.60
    Demografia
    0.60
     CreateTagHelper
    0.57
     AppCompatTheme
    0.57
     "..\..\
    0.57
    lexikon
    0.57
     ModelExpression
    0.55
    Activations Density 0.068%

    No Known Activations