© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15632
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preliminary research findings or results in studies

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

    preliminary research findings

    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
    RTSC
    -0.60
     autorytatywna
    -0.60
     للاسماء
    -0.59
    GEBURTSDATUM
    -0.54
    IndentedString
    -0.52
     cherchés
    -0.51
    yntaxException
    -0.50
    transQ
    -0.50
    expandindo
    -0.49
    انيف
    -0.49
    POSITIVE LOGITS
     preliminary
    2.44
    Preliminary
    2.14
     Preliminary
    2.09
     PRELIM
    1.76
     preliminar
    1.74
    liminary
    1.71
     initial
    1.64
     prelimin
    1.62
    初步
    1.60
    initial
    1.48
    Activations Density 0.193%

    No Known Activations