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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 5046
    Prev
    Next
    INDEX
    Explanations

    numeric values and expressions in mathematical or statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fourth
    -1.23
    Fourth
    -1.19
     fourth
    -1.17
    4
    -1.12
    fourth
    -1.03
    ④
    -0.98
     FOURTH
    -0.98
    FOUR
    -0.94
     quartet
    -0.94
     forties
    -0.90
    POSITIVE LOGITS
     grandmother
    0.60
     cheese
    0.58
     Friday
    0.58
    fifths
    0.56
    pite
    0.56
    cheese
    0.55
     Cheese
    0.54
    Cheese
    0.54
    Friday
    0.54
    setupUi
    0.53
    Activations Density 0.842%

    No Known Activations