© 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. 21-GEMMASCOPE-RES-16K
    6. 3285
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and health-related 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
    는
    -0.59
    //
    -0.59
    tiglie
    -0.57
    yness
    -0.54
     Paglinawan
    -0.54
    #
    -0.54
    wußt
    -0.53
    ⓧ
    -0.53
     Interess
    -0.53
    coroutines
    -0.51
    POSITIVE LOGITS
    ized
    1.99
    ization
    1.80
    izing
    1.71
    istic
    1.69
    isation
    1.65
    ize
    1.55
    ists
    1.44
    izes
    1.39
    istically
    1.37
    ising
    1.34
    Activations Density 0.633%

    No Known Activations