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. 12765
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical issues and their implications

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

    Problems "are", "can", "was", "were" something

    np_acts-logits-general · gemini-2.0-flash

    problems and their resolution

    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
    RefreshLayout
    -0.56
    adpleegd
    -0.55
    HttpFoundation
    -0.52
    yntaxException
    -0.52
    ctest
    -0.49
    RunWith
    -0.47
    segna
    -0.45
    Bibliograf
    -0.45
    czak
    -0.45
    uchter
    -0.44
    POSITIVE LOGITS
     caused
    0.92
    caused
    0.73
     severity
    0.72
     solved
    0.72
     resolved
    0.70
     Caused
    0.70
     incurable
    0.70
     incurred
    0.69
     occurred
    0.69
     occur
    0.68
    Activations Density 0.696%

    No Known Activations