© 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-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2256
    Prev
    Next
    INDEX
    Explanations

    conjunctions and discourse markers that signal addition or connection between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
     <<<<<<<<<<<<<<
    -0.39
    AutoScaleMode
    -0.38
    әрмәләр
    -0.37
     PeEnEo
    -0.36
    onomía
    -0.35
    บุรี
    -0.35
    Personendaten
    -0.34
    rrggbb
    -0.34
     sœurs
    -0.33
    tonsoft
    -0.32
    POSITIVE LOGITS
    tanleria
    0.57
     мәкал
    0.53
    webElementXpaths
    0.52
    etc
    0.52
    Географиясе
    0.51
    PendingIntent
    0.50
     hochzeit
    0.50
     etc
    0.50
    messageInfo
    0.49
    +#+#
    0.47
    Activations Density 0.314%

    No Known Activations