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. 22-GEMMASCOPE-RES-16K
    6. 5995
    Prev
    Next
    INDEX
    Explanations

    technical terms related to video compression and motion vector analysis

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

    Video encoding and codecs

    np_acts-logits-general · gemini-2.0-flash

    video codec encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Catawiki
    -0.62
     Electrochemical
    -0.60
    JpaRepository
    -0.57
    ñata
    -0.55
     cref
    -0.54
     Executes
    -0.54
     tanning
    -0.53
    addington
    -0.53
     smtplib
    -0.53
     répondu
    -0.52
    POSITIVE LOGITS
     video
    0.75
    video
    0.74
    Video
    0.72
     Video
    0.72
     codific
    0.71
     codec
    0.69
     encoding
    0.69
     encode
    0.65
     vidéo
    0.65
     encoder
    0.64
    Activations Density 0.374%

    No Known Activations