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. 22-GEMMASCOPE-RES-16K
    6. 11045
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their contributions

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

    Scandinavian names or surnames

    np_acts-logits-general · gemini-2.0-flash

    Nordic first names and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phép
    -0.47
     proced
    -0.46
     muligt
    -0.45
     pref
    -0.44
     Yên
    -0.43
    mantel
    -0.43
    <?>>
    -0.43
     lenger
    -0.43
     Appro
    -0.42
    lıyor
    -0.42
    POSITIVE LOGITS
    skjaer
    0.77
    findpost
    0.76
     Nielsen
    0.63
     Numerade
    0.62
    RegistryLite
    0.62
    Personensuche
    0.61
     سكانية
    0.61
     Holm
    0.61
     Krist
    0.61
    hede
    0.60
    Activations Density 0.217%

    No Known Activations