© 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. 31486
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of cities and references to notable locations

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

    US locations and associated institutions

    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
     sozinho
    -0.47
    libatkan
    -0.45
     libremente
    -0.39
    relativeTime
    -0.38
     jäm
    -0.38
     recevrez
    -0.38
     berdua
    -0.36
     suun
    -0.36
     käs
    -0.35
     mukana
    -0.35
    POSITIVE LOGITS
    "),
    
    0.57
    ')));
    0.53
    "));
    
    0.53
    ")).
    0.53
    "]
    
    0.52
    ")]
    
    0.52
    '));
    
    0.52
    "])
    
    0.52
    ')))
    0.52
     مُعرِّف
    0.50
    Activations Density 0.046%

    No Known Activations