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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4964
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to buttons and scripts

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

    Tokens related to embedding and sharing content online

    np_acts-logits-general · gemini-2.0-flash

    social media sharing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    posedge
    -0.58
     WebDriverWait
    -0.55
     Lordships
    -0.46
    rxjs
    -0.46
    PDOException
    -0.44
    nodoc
    -0.44
    TimerTask
    -0.44
     nakalista
    -0.44
    WebMethod
    -0.44
     Gewähr
    -0.43
    POSITIVE LOGITS
     share
    1.32
    share
    1.25
     Share
    1.25
     SHARE
    1.24
     sharing
    1.23
    Share
    1.22
     Sharing
    1.16
    SHARE
    1.12
    sharing
    1.12
     shares
    1.05
    Activations Density 0.219%

    No Known Activations