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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7433
    Prev
    Next
    INDEX
    Explanations

    specific phrases or terms related to dining experiences and food orders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chapter
    -0.30
    MethodManager
    -0.29
    primaryStage
    -0.29
    reactstrap
    -0.28
     αποτε
    -0.28
     effectively
    -0.28
     accéder
    -0.28
     even
    -0.28
    KEYCODE
    -0.28
    NonNull
    -0.28
    POSITIVE LOGITS
    OGND
    0.70
    DockStyle
    0.69
    CloseOperation
    0.58
     Савезне
    0.55
     cuz
    0.52
    Tembelea
    0.51
     للاسماء
    0.51
     defaultstate
    0.50
    slideUp
    0.50
     Chwiliwch
    0.49
    Activations Density 0.502%

    No Known Activations