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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 424
    Prev
    Next
    INDEX
    Explanations

    references to fantastical creatures or character types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    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
    Hochspringen
    -0.63
    CppCodeGen
    -0.56
     стаття
    -0.55
    ChildScrollView
    -0.54
     magasiner
    -0.53
    atorial
    -0.52
     activity
    -0.52
    
    -0.51
    position
    -0.51
    NameInMap
    -0.51
    POSITIVE LOGITS
     GoogleFonts
    0.56
     متحده
    0.53
     race
    0.52
     mergeFrom
    0.51
     âgé
    0.50
     насељу
    0.49
     popolazione
    0.49
    fastjson
    0.48
    AnimationsModule
    0.48
     PopupWindow
    0.47
    Activations Density 0.002%

    No Known Activations