© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 23751
    Prev
    Next
    INDEX
    Explanations

    instances of the word "connected" and variations of the term indicating connectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    connected graph, adventure or scheme

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pondi
    -0.44
    cs
    -0.39
    CommandText
    -0.36
    BuildContext
    -0.36
    ProcessEvent
    -0.35
    <bos>
    -0.34
    ouml
    -0.33
    깐
    -0.33
    ms
    -0.32
    matchCondition
    -0.32
    POSITIVE LOGITS
    ness
    0.75
    neſs
    0.57
    NESS
    0.57
     ब्रेकडाउन
    0.56
     Connected
    0.55
     ſta
    0.54
     pleaſure
    0.53
    Connected
    0.51
     faſt
    0.51
    AndEndTag
    0.49
    Activations Density 0.014%

    No Known Activations