© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 91355
    Prev
    Next
    INDEX
    Explanations

    terms related to the design and development of systems, particularly in scientific and technical contexts

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

    design and development of successful products

    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
     recién
    -0.60
     recém
    -0.56
    RectangleBorder
    -0.54
     intptr
    -0.53
    CloseOperation
    -0.52
    findpost
    -0.50
    sizeCache
    -0.50
    setupUi
    -0.49
     JAXBElement
    -0.47
     reciente
    -0.46
    POSITIVE LOGITS
     effective
    0.87
     efficient
    0.86
     successful
    0.74
     reliable
    0.71
     efficacious
    0.67
     efficace
    0.67
     sustainable
    0.66
     truly
    0.66
     efficaces
    0.66
     durable
    0.65
    Activations Density 0.107%

    No Known Activations