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. 18-GEMMASCOPE-RES-16K
    6. 8512
    Prev
    Next
    INDEX
    Explanations

    news-related content, particularly updates and information about various events

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

    news (national, international, breaking)

    np_acts-logits-general · gemini-2.0-flash

    international news and world events

    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
    довлет
    -0.52
    مكان
    -0.48
    vyšší
    -0.44
     alapján
    -0.43
     alluminio
    -0.41
    муля
    -0.41
    Stiftung
    -0.40
    jeva
    -0.40
    CustomAttributes
    -0.40
    Опыт
    -0.38
    POSITIVE LOGITS
     news
    2.41
    news
    1.83
     News
    1.76
    News
    1.68
     NEWS
    1.67
     headlines
    1.52
     noticias
    1.50
    NEWS
    1.49
     nieuws
    1.42
     berita
    1.42
    Activations Density 0.338%

    No Known Activations