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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 25-GEMMASCOPE-RES-16K
    6. 8657
    Prev
    Next
    INDEX
    Explanations

    segments combining rich narrative, technical details, and structured data elements such as formatted contact info, code snippets, and metadata

    oai_token-act-pair · o3-miniTriggered by @yemengyus1

    references to information about entities and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pizarro
    -0.35
     Lovato
    -0.35
     Huxley
    -0.35
     Krueger
    -0.34
     Kirchner
    -0.33
    Personendaten
    -0.33
     autorytatywna
    -0.33
     Esau
    -0.33
     Müller
    -0.33
     Romero
    -0.33
    POSITIVE LOGITS
     Background
    0.38
     Support
    0.38
     Training
    0.38
     Experience
    0.37
     Online
    0.37
     Advertising
    0.36
     Features
    0.36
     Information
    0.36
     Current
    0.35
     Results
    0.35
    Activations Density 39.072%

    No Known Activations