© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 13868
    Prev
    Next
    INDEX
    Explanations

    phrases related to troubleshooting and problem-solving in coding or programming contexts

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

    seeking a solution or example

    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
    WebElementEntity
    -0.62
     Whilst
    -0.61
     whilst
    -0.59
    tanleria
    -0.58
    Whilst
    -0.57
     resourceCulture
    -0.56
     كافة
    -0.55
     sämtliche
    -0.55
     defaultstate
    -0.54
    ivably
    -0.53
    POSITIVE LOGITS
    Maybe
    0.56
     informations
    0.52
     Maybe
    0.52
     maybe
    0.52
     datas
    0.51
    maybe
    0.49
     difer
    0.49
     stupid
    0.49
    Canceled
    0.48
     choo
    0.48
    Activations Density 0.290%

    No Known Activations