Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 1288
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.75
    DockStyle
    -0.67
    ásban
    -0.56
    DoubleQuotes
    -0.56
     насељу
    -0.55
    cupertino
    -0.54
    BagConstraints
    -0.53
     kaarangay
    -0.53
     typelib
    -0.52
     inflater
    -0.52
    POSITIVE LOGITS
    glie
    0.73
    UpInside
    0.61
     properties
    0.55
    properties
    0.51
     kemampuan
    0.50
     PROPERTIES
    0.50
    ソナ
    0.49
    èdent
    0.49
     الرياضيه
    0.49
    وردار
    0.49
    Activations Density 0.831%

    No Known Activations