© 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. 4510
    Prev
    Next
    INDEX
    Explanations

    coding syntax elements, particularly related to output operations

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

    C++ left bit shift operator

    np_acts-logits-general · gemini-2.0-flash

    C++ output streams and agreements

    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
    principalColumn
    -0.95
    bootstrapcdn
    -0.88
    IsMutable
    -0.86
     Мексичка
    -0.79
    oredCriteria
    -0.78
    SourceChecksum
    -0.72
     invokingState
    -0.71
     ComVisible
    -0.70
    KURZBESCHREIBUNG
    -0.70
    addLast
    -0.70
    POSITIVE LOGITS
     endl
    1.13
    endl
    0.83
    <<<<
    0.70
     <<
    0.67
     std
    0.64
    <<<<<<<<
    0.63
    ing
    0.61
    <<
    0.61
    ︎
    0.58
    langle
    0.56
    Activations Density 0.025%

    No Known Activations