© 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. 19-GEMMASCOPE-RES-16K
    6. 10771
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about understanding or clarifying information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unfortunately
    -0.73
     malheureusement
    -0.71
    unfortunately
    -0.69
     сожалению
    -0.68
     purtroppo
    -0.68
     Unfortunately
    -0.65
    Unfortunately
    -0.64
     niestety
    -0.61
     leider
    -0.60
     infeliz
    -0.59
    POSITIVE LOGITS
     surely
    1.54
     Surely
    1.52
    Surely
    1.52
     przecież
    1.30
     Shouldn
    1.30
    Shouldn
    1.18
    难道
    1.10
    不就是
    1.06
    Ведь
    1.04
     ведь
    0.99
    Activations Density 0.453%

    No Known Activations