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. 8-GEMMASCOPE-RES-16K
    6. 8637
    Prev
    Next
    INDEX
    Explanations

    references to the importation and spread of goods or concepts, particularly those associated with trade

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NullException
    -0.50
    setVerticalGroup
    -0.47
    CORBA
    -0.46
    Javadoc
    -0.46
    findpost
    -0.45
     RVA
    -0.45
    گذ
    -0.44
     geç
    -0.44
    Ers
    -0.43
     geçi
    -0.42
    POSITIVE LOGITS
     виправивши
    0.92
    bringing
    0.90
     Bring
    0.88
     bringing
    0.86
     bring
    0.86
    Bring
    0.86
    Brought
    0.85
    bring
    0.84
     BRING
    0.83
     Bringing
    0.82
    Activations Density 0.179%

    No Known Activations