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. 16-GEMMASCOPE-RES-16K
    6. 6332
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need for further research and clarification in scientific studies

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

    Sentences starting with transitional words/phrases

    np_acts-logits-general · gemini-2.0-flash

    need for further investigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.84
     BorderSide
    -0.73
    StreetMap
    -0.72
     Efq
    -0.70
    RectangleBorder
    -0.67
     estekak
    -0.66
     AssemblyTitle
    -0.65
    newArrayList
    -0.62
    IsMutable
    -0.61
    Jeografia
    -0.58
    POSITIVE LOGITS
     uncertain
    0.70
     Investigate
    0.67
     unclear
    0.66
    Investig
    0.66
     investigate
    0.64
     unsure
    0.63
     investig
    0.63
     further
    0.62
     pending
    0.62
     await
    0.62
    Activations Density 0.651%

    No Known Activations