© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    references to exercises and activities in practical scenarios

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

    exercise

    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
    ValueStyle
    -0.52
     surla
    -0.50
    LabelTagHelper
    -0.46
    AddTagHelper
    -0.45
    Vorte
    -0.45
    Derbyniad
    -0.44
     propOrder
    -0.43
    parsedMessage
    -0.42
     Diener
    -0.42
     ***!
    -0.40
    POSITIVE LOGITS
     exercises
    2.09
     exercise
    2.03
     Exercise
    1.81
    exercise
    1.75
    Exercise
    1.74
     Exercises
    1.73
     exercices
    1.66
     exerci
    1.64
    exercises
    1.63
     exercice
    1.62
    Activations Density 0.068%

    No Known Activations