© 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. 66123
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and attributes

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

    software licenses and disclaimers

    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
     
    -0.63
    1
    -0.60
    2
    -0.59
    ,
    -0.54
    s
    -0.51
    3
    -0.50
    _
    -0.50
    h
    -0.49
    ↵
    -0.49
    A
    -0.49
    POSITIVE LOGITS
     queſta
    1.37
    rungsseite
    1.20
    OGND
    1.19
     Мексичка
    1.15
     ſind
    1.13
     kasarigan
    1.11
    GEBURTSDATUM
    1.10
    ésultats
    1.09
    httphttps
    1.07
     незавершена
    1.03
    Activations Density 0.001%

    No Known Activations