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. 5-GEMMASCOPE-RES-16K
    6. 4859
    Prev
    Next
    INDEX
    Explanations

    special formatting elements, particularly those related to typesetting and captions in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetes
    -0.67
     snippetHide
    -0.64
    ParallelGroup
    -0.61
    addContainerGap
    -0.61
     kasarigan
    -0.58
     NavController
    -0.55
    hwar
    -0.55
    KeySpec
    -0.50
    stylesheet
    -0.50
    wakili
    -0.50
    POSITIVE LOGITS
    *{
    1.12
     Chwiliwch
    0.80
    *{-
    0.75
     betweenstory
    0.75
     pinulongan
    0.69
    LookAnd
    0.69
    InstrumentedTest
    0.68
    ỡng
    0.66
     gyhoeddwyd
    0.62
    TestingModule
    0.62
    Activations Density 0.060%

    No Known Activations