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. 10714
    Prev
    Next
    INDEX
    Explanations

    words associated with construction, creation, or development processes

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

    "build" or its variations

    np_acts-logits-general · gemini-2.0-flash

    build a or up

    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
     <<<<<<<<<<<<<<
    -0.76
     Italijani
    -0.63
    ésultat
    -0.58
     contextLoads
    -0.56
     /\.
    -0.55
    awaiter
    -0.54
    getWriter
    -0.54
    
    -0.54
    /*---
    -0.54
    PreferredItem
    -0.53
    POSITIVE LOGITS
    BUILD
    1.15
     BUILD
    1.08
    builds
    1.03
     builds
    1.02
     built
    1.00
     Builds
    0.98
     Build
    0.97
     build
    0.96
    Built
    0.96
    Builds
    0.93
    Activations Density 0.055%

    No Known Activations