© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 5884
    Prev
    Next
    INDEX
    Explanations

    code structures related to data categories and menu items in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.59
     $_"
    -0.57
    KURZBESCHREIBUNG
    -0.56
     {},
    
    -0.56
    {}{}
    -0.54
    )");
    
    -0.53
    ')")
    -0.53
    errHandler
    -0.53
     Majefty
    -0.52
     ―――――
    -0.52
    POSITIVE LOGITS
     "
    1.95
     “
    1.85
    「
    1.73
     «
    1.60
    ("
    1.57
     '
    1.52
     „
    1.52
     ‘
    1.48
     「
    1.47
    、「
    1.42
    Activations Density 0.877%

    No Known Activations