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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 99025
    Prev
    Next
    INDEX
    Explanations

    references to personal development and coaching

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

    coaching, authoring, promoting, teaching

    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
     betweenstory
    -0.62
    parsedMessage
    -0.57
    oredCriteria
    -0.49
     numerus
    -0.46
     &___
    -0.44
    AnchorStyles
    -0.44
    CodedInputStream
    -0.43
     Roskov
    -0.41
    ErrUnexpectedEOF
    -0.41
     Taktlose
    -0.41
    POSITIVE LOGITS
     المعيارى
    0.52
     محفوظة
    0.50
    romyalgia
    0.50
     coaching
    0.48
    romyal
    0.40
     influencer
    0.40
    ніципалі
    0.39
    
    0.39
     MLM
    0.39
     teachings
    0.38
    Activations Density 0.028%

    No Known Activations