© 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
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 6955
    Prev
    Next
    INDEX
    Explanations

    phrases related to copyright and licensing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ken
    -0.44
     Hill
    -0.38
     wart
    -0.37
    Hill
    -0.36
     ag
    -0.35
    Ken
    -0.33
    akim
    -0.33
     nin
    -0.33
     Ting
    -0.32
     Raman
    -0.32
    POSITIVE LOGITS
    httphttps
    0.59
    دانشنامهٔ
    0.57
    Jeografia
    0.57
     الاطلاع
    0.53
    haikusbot
    0.51
    Personendaten
    0.50
     חיצוניים
    0.49
    afficheront
    0.48
     مشين
    0.47
    
    0.47
    Activations Density 1.143%

    No Known Activations