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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7928
    Prev
    Next
    INDEX
    Explanations

    references to social media and online engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.56
    Tembelea
    -0.44
    তথ্যসূত্র
    -0.44
    MigrationBuilder
    -0.41
    spesies
    -0.39
     propOrder
    -0.38
     مشارکت‌کنندگان
    -0.38
    JAXB
    -0.38
    udy
    -0.36
     surla
    -0.36
    POSITIVE LOGITS
     Facebook
    0.77
     facebook
    0.70
     Twitter
    0.67
     Instagram
    0.66
     social
    0.64
     instagram
    0.63
    Facebook
    0.63
     twitter
    0.63
    社交
    0.61
    facebook
    0.58
    Activations Density 0.123%

    No Known Activations