© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14029
    Prev
    Next
    INDEX
    Explanations

    phrases that signal conjunctions and transitions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.99
     Roskov
    -0.97
    SharedDtor
    -0.96
    XmlAccessType
    -0.94
    Personendaten
    -0.93
    Autoritní
    -0.93
    SequentialGroup
    -0.93
    principalColumn
    -0.90
     estekak
    -0.89
     chi̍t
    -0.88
    POSITIVE LOGITS
     yes
    0.87
     don
    0.85
     why
    0.81
     then
    0.80
     if
    0.75
     how
    0.74
     hey
    0.72
     speaking
    0.72
     who
    0.72
     importantly
    0.71
    Activations Density 0.153%

    No Known Activations