© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12273
    Prev
    Next
    INDEX
    Explanations

    references to frame rate and frame interpolation in technical contexts

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

    "frame" followed by rate/is/generating/for/between

    np_acts-logits-general · gemini-2.0-flash

    frame rate conversion, interpolation

    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
    سكري
    -0.54
    enumii
    -0.50
    ्ञ
    -0.48
    íncia
    -0.46
     Pingback
    -0.46
     rodzaju
    -0.44
     Ammon
    -0.44
    afin
    -0.44
    PathParam
    -0.43
     leta
    -0.43
    POSITIVE LOGITS
    works
    0.67
    less
    0.67
    Rate
    0.66
    ViewFeatures
    0.66
     rate
    0.66
    msgSender
    0.65
    WORK
    0.62
    buffer
    0.62
     frames
    0.61
     kerja
    0.60
    Activations Density 0.098%

    No Known Activations