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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 38793
    Prev
    Next
    INDEX
    Explanations

    terms related to broadcasting and airing television programs

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

    airing news and shows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cappuccio
    -0.44
    Архівовано
    -0.42
     ahorro
    -0.39
    pegno
    -0.38
     infancia
    -0.38
     transparencia
    -0.37
     agência
    -0.37
     Mejora
    -0.37
    IContainer
    -0.36
     desconocido
    -0.36
    POSITIVE LOGITS
     aired
    0.57
     broadcast
    0.57
    TemporalType
    0.54
    held
    0.49
     Broadcast
    0.49
     airing
    0.49
     circulate
    0.47
     thiệu
    0.47
     airs
    0.47
     sung
    0.47
    Activations Density 0.042%

    No Known Activations