© 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. 20-GEMMASCOPE-RES-131K
    6. 127365
    Prev
    Next
    INDEX
    Explanations

    instances of the word "describe" and its variants

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

    introducing descriptions

    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
    jsonwebtoken
    -0.58
    ougars
    -0.57
    ungeon
    -0.56
    Malley
    -0.54
    ########.
    -0.54
     Bally
    -0.53
     Boomer
    -0.53
    Leary
    -0.53
    waitKey
    -0.52
     cornstarch
    -0.52
    POSITIVE LOGITS
     Describe
    1.11
     describe
    1.05
     description
    1.05
     DESCR
    1.03
     describes
    1.02
    describe
    0.98
     described
    0.98
     describing
    0.96
    Describe
    0.95
     décrire
    0.94
    Activations Density 0.053%

    No Known Activations