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. 308
    Prev
    Next
    INDEX
    Explanations

    terms related to food, culture, and societal behaviors

    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
    شهاد
    -0.59
     anſ
    -0.54
     rät
    -0.53
    lelő
    -0.52
     ***!
    -0.52
     inaction
    -0.51
     quitt
    -0.51
     száll
    -0.51
     raiſ
    -0.50
    тли
    -0.50
    POSITIVE LOGITS
     sneaking
    1.54
     sneak
    1.50
     sne
    1.27
     crept
    1.22
    sneak
    1.18
     creeping
    1.18
     Sneak
    1.15
     slipped
    1.13
    Sneak
    1.07
     infiltrated
    1.03
    Activations Density 0.439%

    No Known Activations