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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75357
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical arguments or punctuation related to function calls in programming code

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

    function arguments argc and argv

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AsUp
    -0.74
     BorderSide
    -0.71
     betweenstory
    -0.69
    tanleria
    -0.68
     ſei
    -0.62
     beſch
    -0.61
     ddelwed
    -0.60
     imagui
    -0.60
     verſch
    -0.60
     ſehr
    -0.59
    POSITIVE LOGITS
     argc
    0.56
    AutoScaleMode
    0.39
     CreateTagHelper
    0.38
     requestCode
    0.36
    argc
    0.34
    Hochspringen
    0.32
    AntiForgeryToken
    0.30
     AttributeSet
    0.29
    Einzelnachweise
    0.29
    RTLI
    0.29
    Activations Density 0.001%

    No Known Activations