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. 12-GEMMASCOPE-RES-16K
    6. 6253
    Prev
    Next
    INDEX
    Explanations

    references to specific lakes and bodies of water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Foer
    -0.85
     Machu
    -0.83
     متعلقه
    -0.78
     religieux
    -0.75
     SqlCommand
    -0.74
    ouple
    -0.74
    GIVEREF
    -0.74
     Perci
    -0.74
     >=",
    -0.73
    szy
    -0.73
    POSITIVE LOGITS
     lakes
    1.95
     Lake
    1.95
     lake
    1.89
    Lake
    1.74
     Lakes
    1.70
    Lakes
    1.57
     LAKE
    1.56
    lakes
    1.54
    lake
    1.53
    LAKE
    1.39
    Activations Density 0.082%

    No Known Activations