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. 20-GEMMASCOPE-RES-16K
    6. 5277
    Prev
    Next
    INDEX
    Explanations

    references to cameras and related equipment

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

    following "camera"

    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 @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HostException
    -0.91
     للمعارف
    -0.79
    URLException
    -0.72
     виправивши
    -0.66
    rungsseite
    -0.65
     Вікі
    -0.63
    homonymie
    -0.62
     الرياضيه
    -0.61
    ntos
    -0.61
     Crusoe
    -0.59
    POSITIVE LOGITS
    corder
    0.71
     Camara
    0.67
     Camer
    0.66
    Cameras
    0.65
     cameras
    0.64
     obs
    0.64
     lens
    0.64
    Camer
    0.62
     Cameras
    0.62
    ToObject
    0.62
    Activations Density 0.125%

    No Known Activations