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. 19-GEMMASCOPE-RES-16K
    6. 3015
    Prev
    Next
    INDEX
    Explanations

    keywords related to digital and social media sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Override
    -0.55
    TextWatcher
    -0.54
    Bürger
    -0.53
    AndEndTag
    -0.52
    Bioaccumulative
    -0.51
    lamydia
    -0.48
    TimerTask
    -0.47
     monopo
    -0.47
    argli
    -0.47
    (")");
    -0.46
    POSITIVE LOGITS
     inspiration
    1.67
    Inspiration
    1.51
    inspiration
    1.50
     Inspiration
    1.50
     inspirations
    1.41
     inspira
    1.28
     inspirational
    1.23
     inspire
    1.23
     inspiri
    1.22
     inspiring
    1.21
    Activations Density 0.138%

    No Known Activations