© 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. 121268
    Prev
    Next
    INDEX
    Explanations

    statistical metrics and confidence intervals related to clinical research outcomes

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

    95 confidence intervals

    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
     queſta
    -1.00
     tartalomajánló
    -0.86
    ſelf
    -0.84
    تقاوى
    -0.82
     surla
    -0.79
    hyrchwyd
    -0.79
     betweenstory
    -0.78
    IUrlHelper
    -0.77
    ſelves
    -0.76
    :✨
    -0.75
    POSITIVE LOGITS
     
    0.34
     C
    0.30
      
    0.29
    ,
    0.29
     c
    0.28
    setVerticalGroup
    0.27
     [
    0.27
    C
    0.27
    1
    0.27
     re
    0.26
    Activations Density 0.182%

    No Known Activations