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. 3102
    Prev
    Next
    INDEX
    Explanations

    references to programming and code structure

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

    Code, programming, or scripting syntax

    np_acts-logits-general · gemini-2.0-flash

    code snippets and programming terms

    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
    Zeneca
    -0.45
    rawQuery
    -0.45
     screw
    -0.44
     invasión
    -0.43
     Arxivat
    -0.42
    였다
    -0.42
     فار
    -0.42
    دانشنامهٔ
    -0.41
     tham
    -0.38
    経
    -0.38
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.76
    WriteTagHelper
    0.75
    WaitGroup
    0.70
     @"/
    0.67
     []:
    0.66
    VYMaps
    0.66
    تفصیلات
    0.65
    Gambas
    0.65
    windowFixed
    0.65
     MainAxisSize
    0.65
    Activations Density 0.064%

    No Known Activations