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. 6807
    Prev
    Next
    INDEX
    Explanations

    technical terminology and concepts related to specific fields or disciplines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    IsContent
    -0.70
    全文
    -0.60
     alguien
    -0.58
     vieles
    -0.58
     Autorizaciones
    -0.57
    someone
    -0.56
    apnews
    -0.56
    JNIEnv
    -0.54
    Hauptartikel
    -0.53
    things
    -0.53
    POSITIVE LOGITS
    fjspx
    0.90
     such
    0.67
     different
    0.61
     dezelfde
    0.60
     various
    0.59
     whatever
    0.59
     paziente
    0.58
     diferite
    0.57
     medesimo
    0.56
     certain
    0.54
    Activations Density 0.834%

    No Known Activations