© 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. 20-GEMMASCOPE-RES-131K
    6. 123076
    Prev
    Next
    INDEX
    Explanations

    advanced technology features in vehicles

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

    technology and systems

    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
     libremente
    -0.43
     Harian
    -0.36
     espoir
    -0.36
     peggio
    -0.35
     agrav
    -0.35
     Strahl
    -0.35
     calzado
    -0.34
     unwillingness
    -0.34
    FileStream
    -0.33
    yszcz
    -0.33
    POSITIVE LOGITS
     propOrder
    0.62
     gadgets
    0.60
    LabelTagHelper
    0.59
     gadget
    0.54
    technology
    0.54
     technologies
    0.54
     tecnológica
    0.54
    Technologies
    0.53
    technologies
    0.52
    Technology
    0.50
    Activations Density 0.020%

    No Known Activations