© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9720
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and constructs, particularly those associated with setting up tools and actions in a frontend context

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

    Values associated with code or data structures

    np_acts-logits-general · gemini-2.0-flash

    entity, process, host, user

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     
    -0.74
     a
    -0.63
     in
    -0.62
     on
    -0.58
    ,
    -0.58
     (
    -0.58
      
    -0.52
     to
    -0.52
    <eos>
    -0.51
     at
    -0.51
    POSITIVE LOGITS
     resourceCulture
    1.21
    
    1.19
    хьтан
    1.13
     pinulongan
    1.12
    Personendaten
    1.12
    LookAnd
    1.11
    تقاوى
    1.09
    Autoritní
    1.07
     صوتيه
    1.07
    AndEndTag
    1.05
    Activations Density 0.724%

    No Known Activations