Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 20427
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional and spiritual well-being, particularly focusing on religion and its impact on mental health

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

    religious, aquatic, metabolic, physical

    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
    ReusableCell
    -0.47
    Халык
    -0.46
     trouw
    -0.44
    spf
    -0.44
    beve
    -0.42
    avond
    -0.42
    proken
    -0.42
     läh
    -0.41
     Naturs
    -0.41
    breakpoints
    -0.40
    POSITIVE LOGITS
    expandindo
    0.52
    ंदीखरीदारी
    0.50
    XmlAccessorType
    0.50
    хьтан
    0.50
     старости
    0.45
    
    0.43
     HttpNotFound
    0.42
     transférez
    0.42
    évaluateur
    0.41
    sidemargin
    0.41
    Activations Density 0.056%

    No Known Activations