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. 11747
    Prev
    Next
    INDEX
    Explanations

    terms indicating the action or state of flying

    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
    XmlAccessorType
    -0.93
    ItemBackground
    -0.83
     Alcott
    -0.83
    TextHelper
    -0.82
    بوابة
    -0.81
     Bassett
    -0.80
    RectangleBorder
    -0.79
     Tangerang
    -0.79
    UnknownFieldSet
    -0.78
     MainAxisSize
    -0.77
    POSITIVE LOGITS
     FLY
    1.48
     fly
    1.47
     Fly
    1.45
     flies
    1.33
    FLY
    1.30
    Fly
    1.27
    fly
    1.27
     flying
    1.17
     Flies
    1.17
     Flying
    1.13
    Activations Density 0.035%

    No Known Activations