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. 13786
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or constructs related to operators and functions

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

    LaTeX math mode delimiters

    np_acts-logits-general · gemini-2.0-flash

    Mathematical notation and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    sidemargin
    -0.71
     المعيارى
    -0.56
    BeforeClass
    -0.55
     MessageBoxIcon
    -0.55
    pulumi
    -0.54
    AsUp
    -0.53
     useParams
    -0.53
    {{/
    -0.53
     ddelweddau
    -0.53
     FetchType
    -0.53
    POSITIVE LOGITS
    SourceChecksum
    0.85
     للاسماء
    0.82
    mtable
    0.81
     snippetHide
    0.73
    :✨
    0.72
     ISNI
    0.64
     الحره
    0.63
     Saltar
    0.62
    новниш
    0.62
    帖最后由
    0.61
    Activations Density 0.748%

    No Known Activations