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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 9328
    Prev
    Next
    INDEX
    Explanations

    elements related to technology and advancements in skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.54
    ieb
    -0.51
     Presidencia
    -0.49
      
    -0.46
    configure
    -0.45
     chuyển
    -0.45
     $
    -0.45
    EVT
    -0.45
    DeleteBehavior
    -0.44
     Schö
    -0.44
    POSITIVE LOGITS
     الرياضيه
    0.84
    protoimpl
    0.84
     '\\;'
    0.75
     sonno
    0.75
     فريبيس
    0.69
     pymongo
    0.69
    imakasih
    0.68
    iastes
    0.66
     للمعارف
    0.66
     poichè
    0.65
    Activations Density 0.662%

    No Known Activations