© 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. 20-GEMMASCOPE-RES-131K
    11. 103274
    Prev
    Next
    INDEX
    Explanations

    instances of doubt or negativity in the context of experiences and opinions

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

    if not for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.63
    webElementXpaths
    -0.63
    الحياه
    -0.60
     pleaſure
    -0.57
     purpoſe
    -0.57
    SharedDtor
    -0.56
     greateſt
    -0.56
    DockStyle
    -0.54
     pinulongan
    -0.54
     reaſon
    -0.53
    POSITIVE LOGITS
    要不是
    0.44
    posedge
    0.43
    videoId
    0.40
    offsetof
    0.36
     Would
    0.35
     WOULD
    0.34
    Would
    0.34
     consultato
    0.34
     had
    0.33
     fosse
    0.33
    Activations Density 0.011%

    No Known Activations