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. 8669
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific programming syntax and structure related to software libraries or packages

    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
    TagMode
    -0.58
    BASEPATH
    -0.53
    WriteAttribute
    -0.52
    Geografie
    -0.52
    submitted
    -0.52
    ">—
    -0.52
    baomidou
    -0.51
    δρ
    -0.51
    urlpatterns
    -0.51
    ibatis
    -0.50
    POSITIVE LOGITS
    Hdr
    0.64
    apache
    0.59
    AxisAlignment
    0.57
    tdessen
    0.57
     Roskov
    0.57
     otomatig
    0.56
    __(/*!
    0.54
     TÉCN
    0.53
     Económica
    0.52
     esprits
    0.52
    Activations Density 0.061%

    No Known Activations