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. 10975
    Prev
    Next
    INDEX
    Explanations

    references to video and audio production roles and technologies

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

    Video production and broadcasting

    np_acts-logits-general · gemini-2.0-flash

    audio, video, and broadcast production

    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
    Aktualisiert
    -0.56
     suspensão
    -0.51
     voks
    -0.50
     fotográfico
    -0.49
     refusé
    -0.48
     ordinaires
    -0.47
    åringen
    -0.45
     privées
    -0.45
    Typing
    -0.44
     razonable
    -0.44
    POSITIVE LOGITS
     Broadcast
    0.77
     editing
    0.76
     production
    0.75
     SDI
    0.75
     broadcast
    0.72
     workflow
    0.72
     Production
    0.72
     productions
    0.70
     edit
    0.70
     Editing
    0.69
    Activations Density 0.215%

    No Known Activations