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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14882
    Prev
    Next
    INDEX
    Explanations

    references to media coverage and its impact on public perception

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

    news outlets

    np_acts-logits-general · gemini-2.0-flash

    news media and journalism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ssil
    -0.40
    Diweddarwch
    -0.38
     Prairie
    -0.36
     tinker
    -0.36
    DockStyle
    -0.36
     незавершена
    -0.35
    RuleContext
    -0.34
    newBuilder
    -0.34
     relax
    -0.34
     GP
    -0.34
    POSITIVE LOGITS
     journalistic
    0.73
     journalists
    0.72
     berita
    0.70
     reporters
    0.69
    報道
    0.68
     journalistes
    0.67
     reportage
    0.65
     noticia
    0.65
     news
    0.65
     novin
    0.63
    Activations Density 0.263%

    No Known Activations