© 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. 5404
    Prev
    Next
    INDEX
    Explanations

    casual conversational phrases and questions indicating uncertainty or inquiry

    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
    =$?
    -0.59
    ьаж
    -0.57
    CodedInputStream
    -0.55
     loob
    -0.49
    Sub
    -0.48
    }?>
    -0.48
     hecho
    -0.48
    WithIOException
    -0.47
     vänt
    -0.46
    ficador
    -0.45
    POSITIVE LOGITS
     SafeMath
    0.69
    ActionCreators
    0.66
    DataAnnotations
    0.64
     Tch
    0.61
     Altstadt
    0.60
     noDo
    0.56
    LayoutPanel
    0.56
     IndexPath
    0.55
    InputBorder
    0.55
    romechanical
    0.54
    Activations Density 0.058%

    No Known Activations