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. 12-GEMMASCOPE-RES-16K
    6. 12064
    Prev
    Next
    INDEX
    Explanations

    HTML document structure elements and formatting tags

    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
     Friedman
    -0.69
    álás
    -0.66
     Sơn
    -0.66
     Hyman
    -0.64
     McClellan
    -0.63
     Biel
    -0.62
     Hobson
    -0.61
     هيا
    -0.61
     Swann
    -0.60
    kitab
    -0.60
    POSITIVE LOGITS
    enumerate
    1.21
     Audiodateien
    1.02
     الحره
    0.97
     }}"></
    0.96
    ();)
    0.94
    "):
    
    0.92
    ViewFeatures
    0.90
    '):
    
    0.90
    IsContent
    0.89
    extAlignment
    0.89
    Activations Density 0.004%

    No Known Activations