© 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. 18-GEMMASCOPE-RES-16K
    6. 2139
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions involving variables

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

    Hexadecimal representations

    np_acts-logits-general · gemini-2.0-flash

    D / d prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.54
    oneofs
    -0.50
    SequentialGroup
    -0.47
     XMLHttpRequest
    -0.46
     Majefty
    -0.44
    [*
    -0.43
     AdapterView
    -0.43
     Chama
    -0.42
     laft
    -0.42
    पया
    -0.42
    POSITIVE LOGITS
     D
    1.01
    D
    0.84
     David
    0.82
     d
    0.80
     DC
    0.76
     double
    0.72
     dB
    0.71
     digital
    0.71
    David
    0.71
    DC
    0.71
    Activations Density 0.992%

    No Known Activations