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. 21-GEMMASCOPE-RES-16K
    6. 663
    Prev
    Next
    INDEX
    Explanations

    discussions about sensitive topics and family planning issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     дописавши
    -0.59
    multline
    -0.57
    NameValuePair
    -0.57
    перь
    -0.56
    checkmark
    -0.54
    TextUtils
    -0.52
     RoutedEventArgs
    -0.52
    FontAwesomeIcon
    -0.51
    rowse
    -0.51
    ABAD
    -0.50
    POSITIVE LOGITS
     topic
    3.06
     topics
    2.75
     subject
    2.75
     Topic
    2.35
     subjects
    2.32
    subject
    2.27
    Topic
    2.22
    topic
    2.21
     issue
    2.14
     sujets
    2.12
    Activations Density 0.575%

    No Known Activations