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. 16-GEMMASCOPE-RES-16K
    6. 12175
    Prev
    Next
    INDEX
    Explanations

    references to different types of cameras and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "camera" followed by verbs relating to position or movement

    np_acts-logits-general · gemini-2.0-flash

    camera pose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    downs
    -0.73
    URLException
    -0.69
    AsUp
    -0.66
    protoimpl
    -0.64
    sstil
    -0.64
    #
    -0.62
    astify
    -0.62
     Ugo
    -0.60
     Adkins
    -0.56
    *}[
    -0.55
    POSITIVE LOGITS
    Cameras
    0.81
    kamer
    0.77
     Camer
    0.77
     kamer
    0.77
     cameras
    0.76
    Bibliograf
    0.75
     Cristi
    0.74
     Cameras
    0.74
    Ārējās
    0.74
    nonatomic
    0.73
    Activations Density 0.090%

    No Known Activations