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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129912
    Prev
    Next
    INDEX
    Explanations

    elements related to news broadcasting and television networks

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

    major television networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.50
    sidemargin
    -0.45
     Spotify
    -0.45
     Picchu
    -0.45
    util
    -0.39
    Spotify
    -0.39
     podcast
    -0.38
     Fier
    -0.37
     podcasts
    -0.37
     Poison
    -0.36
    POSITIVE LOGITS
     network
    0.69
     networks
    0.65
     CBS
    0.59
     NBC
    0.56
     ABC
    0.56
    CBS
    0.54
    network
    0.52
    ABC
    0.51
     Networks
    0.51
     Network
    0.50
    Activations Density 0.100%

    No Known Activations