© 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. 13716
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related keywords in programming contexts

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

    successfully packaged

    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
     unpopular
    -0.63
     dislikes
    -0.59
    ]=-
    -0.56
     unattractive
    -0.56
    Yikes
    -0.56
     disadvantages
    -0.56
     mauvais
    -0.54
     unsuitable
    -0.54
     unfortunate
    -0.52
     unwelcome
    -0.52
    POSITIVE LOGITS
     success
    1.38
     successful
    1.37
    Success
    1.24
    success
    1.24
     successes
    1.22
     Success
    1.20
     successfully
    1.16
     Successful
    1.16
     SUCCESS
    1.16
    SUCCESS
    1.15
    Activations Density 0.147%

    No Known Activations