© 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. 17-GEMMASCOPE-RES-16K
    6. 13778
    Prev
    Next
    INDEX
    Explanations

    phrases that express emphasis or validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.64
     Efq
    -0.58
     sukienka
    -0.56
     avoient
    -0.54
    олові
    -0.51
     appartements
    -0.51
     kurtka
    -0.51
     Appellee
    -0.51
     triomphe
    -0.50
     Theſe
    -0.50
    POSITIVE LOGITS
    曖昧さ回避
    0.94
     nakalista
    0.88
    Personendaten
    0.81
     архивлан
    0.74
     defaultstate
    0.69
    WaitGroup
    0.69
     autorytatywna
    0.68
     a
    0.66
     disambiguazione
    0.64
    Cyfeiriadau
    0.64
    Activations Density 0.111%

    No Known Activations