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. 22-GEMMASCOPE-RES-16K
    6. 13954
    Prev
    Next
    INDEX
    Explanations

    phrases related to high performance or quality in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     canina
    -0.53
     Dede
    -0.52
    ByVersion
    -0.51
     zape
    -0.49
    tagHelperRunner
    -0.49
     nhàng
    -0.49
    RuleContext
    -0.49
    edly
    -0.48
     otak
    -0.47
     Lordships
    -0.47
    POSITIVE LOGITS
    WriteBarrier
    0.64
    SerializedSize
    0.64
    Vidite
    0.60
    queryInterface
    0.59
     purity
    0.58
     strength
    0.56
     [{
    
    0.53
     efficiency
    0.50
    pellier
    0.49
     definition
    0.49
    Activations Density 0.161%

    No Known Activations