© 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. 24-GEMMASCOPE-RES-16K
    11. 1693
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associations in various contexts

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

    numbers, especially the number 3

    np_acts-logits-general · gemini-2.0-flash

    numbers and words for "three"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.93
    Fifth
    -0.89
    findpost
    -0.87
     fifth
    -0.85
     Fifth
    -0.84
     sixth
    -0.84
    fifth
    -0.80
    SequentialGroup
    -0.78
    fjspx
    -0.78
    Sixth
    -0.76
    POSITIVE LOGITS
    3
    1.81
    ３
    1.18
     three
    1.07
     Three
    1.03
    三
    0.98
     tiga
    0.97
    ۳
    0.96
     trois
    0.95
     ۳
    0.91
     ३
    0.91
    Activations Density 1.659%

    No Known Activations