Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 6044
    Prev
    Next
    INDEX
    Explanations

    the presence of different sections in a document structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     layui
    -0.62
     Dage
    -0.55
    getEnd
    -0.55
    endar
    -0.54
     BorderRadius
    -0.52
    AsUp
    -0.52
     end
    -0.51
     RISE
    -0.51
    lets
    -0.51
    END
    -0.50
    POSITIVE LOGITS
    section
    3.23
    subsubsection
    1.92
    subsection
    1.84
    sections
    1.69
     section
    1.51
    Section
    1.38
     sections
    1.32
    SECTION
    1.30
     Section
    1.21
    Sections
    1.20
    Activations Density 0.016%

    No Known Activations