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. 16-GEMMASCOPE-RES-16K
    6. 6693
    Prev
    Next
    INDEX
    Explanations

    references to live television broadcasts or shows

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

    Television or radio broadcasting

    np_acts-logits-general · gemini-2.0-flash

    broadcast television and radio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CDP
    -0.50
    uxxxx
    -0.50
     stihl
    -0.48
    DeleteBehavior
    -0.45
     padel
    -0.45
     work
    -0.44
    ItemBackground
    -0.44
     paddock
    -0.44
    MPP
    -0.43
     typewriter
    -0.42
    POSITIVE LOGITS
     broadcast
    1.11
     broadcasts
    1.07
     broadcasting
    1.05
     television
    1.03
     Television
    0.96
     televis
    0.95
     broadcasters
    0.94
     radio
    0.94
     Broadcasting
    0.94
    television
    0.92
    Activations Density 0.254%

    No Known Activations