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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1285
    Prev
    Next
    INDEX
    Explanations

    specific programming-related terms and keywords associated with tool classes and their functionalities

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

    Abbreviations of "Circuit" and similar terms

    np_acts-logits-general · gemini-2.0-flash

    legal citations and code turn markers

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ">//
    -0.48
    httphttps
    -0.44
     hề
    -0.41
    initState
    -0.41
     Sequelize
    -0.39
    complexContent
    -0.39
     spurs
    -0.37
    
    -0.37
    scrollTop
    -0.36
    migrationBuilder
    -0.36
    POSITIVE LOGITS
     للاسماء
    0.58
     Numerade
    0.56
    oredCriteria
    0.49
    windowFixed
    0.49
    LEncoder
    0.42
     transfieras
    0.42
    WithIOException
    0.41
    ✨:
    0.41
    cinfo
    0.41
     الرياضيه
    0.40
    Activations Density 0.019%

    No Known Activations