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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1171
    Prev
    Next
    INDEX
    Explanations

    mentions of companies and their announcements related to financial matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.86
    featureID
    -0.77
    ConstraintMaker
    -0.73
    WriteBarrier
    -0.69
     autorytatywna
    -0.65
    олові
    -0.61
    EndGlobalSection
    -0.61
    شهاد
    -0.60
    -------------</
    -0.60
    hyrchwyd
    -0.60
    POSITIVE LOGITS
     announces
    0.75
     today
    0.75
     announced
    0.69
     announce
    0.67
     announcement
    0.66
    today
    0.66
    announce
    0.66
     Announcement
    0.61
    PRNewswire
    0.60
     ANNOUNC
    0.60
    Activations Density 0.079%

    No Known Activations