© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16179
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and structures related to logical conditions and control flow statements

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

    Boolean logic operators

    np_acts-logits-general · gemini-2.0-flash

    logical operators and conjunctions

    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
    __':
    
    -1.14
    SharedDtor
    -1.12
    =$?
    -1.07
    RenderAtEndOf
    -1.07
    __":
    
    -1.02
     typelib
    -1.00
     '\\;'
    -0.97
    yntaxException
    -0.95
    ViewFeatures
    -0.95
    TagMode
    -0.94
    POSITIVE LOGITS
     AND
    1.79
    AND
    1.41
     OR
    1.29
     And
    1.15
     &&
    1.13
    OR
    1.07
    And
    1.06
    且
    0.84
     BUT
    0.80
    かつ
    0.80
    Activations Density 0.422%

    No Known Activations