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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12701
    Prev
    Next
    INDEX
    Explanations

    key points related to the significance and impact of various topics, particularly in research and importance in societal contexts

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

    Follows words indicating significance or impact

    np_acts-logits-general · gemini-2.0-flash

    abstract qualitiesachieve or impact

    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
     ویکی‌پدی
    -0.74
    +#+#
    -0.71
     فريبيس
    -0.71
     NSCoder
    -0.69
    Чыгана
    -0.68
     GenerationType
    -0.67
     للاسماء
    -0.66
    WithIOException
    -0.65
     الحره
    -0.65
    ſicht
    -0.65
    POSITIVE LOGITS
    ujudkan
    0.34
     ti
    0.33
    rungsseite
    0.32
     ter
    0.30
     far
    0.29
     pořád
    0.28
     serious
    0.27
     value
    0.26
    ؤول
    0.25
    为止
    0.25
    Activations Density 0.468%

    No Known Activations