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. 24-GEMMASCOPE-RES-16K
    6. 16292
    Prev
    Next
    INDEX
    Explanations

    technical terms related to frame and motion interpolation processes

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

    "frame" or "frames"

    np_acts-logits-general · gemini-2.0-flash

    video frames or physical frames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    city
    -0.61
     chimique
    -0.61
     CITY
    -0.60
    City
    -0.56
     Paglinawan
    -0.56
     City
    -0.54
    CITY
    -0.54
     تضيفلها
    -0.53
     chemical
    -0.53
    WebServlet
    -0.52
    POSITIVE LOGITS
     frame
    4.42
    frame
    3.93
     Frame
    3.86
     frames
    3.73
    Frame
    3.60
     FRAME
    3.43
     Frames
    3.27
    FRAME
    3.18
    frames
    3.03
    Frames
    2.88
    Activations Density 0.210%

    No Known Activations