Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 14449
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to radio and radiation

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

    radio, TV, broadcasting, and frequencies

    np_acts-logits-general · gemini-2.0-flash

    words related to radio and TV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Профиль
    -0.60
    DAP
    -0.56
     Exacts
    -0.55
    memoized
    -0.52
     CreateTagHelper
    -0.52
     useEffect
    -0.52
     vulgaires
    -0.52
    ]")]
    -0.51
     calldata
    -0.51
     IActionResult
    -0.51
    POSITIVE LOGITS
    
    0.84
     broadcasts
    0.68
     stations
    0.66
     Television
    0.63
     Fernseh
    0.61
     broadcasting
    0.61
     televisions
    0.60
     broadcast
    0.60
     television
    0.60
    Television
    0.59
    Activations Density 0.304%

    No Known Activations