© 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. 15-GEMMASCOPE-RES-16K
    6. 5662
    Prev
    Next
    INDEX
    Explanations

    buttons and their associated classes in HTML code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tation
    -0.71
    eX
    -0.71
     Puck
    -0.69
    boxy
    -0.69
    
    -0.69
    CLE
    -0.69
    e
    -0.67
     Bade
    -0.67
    %%%%%%%%%%%%%%%%
    -0.66
    gada
    -0.66
    POSITIVE LOGITS
    httphttps
    1.21
     btn
    1.18
     Yeats
    0.93
    btn
    0.93
    lève
    0.85
    ########.
    0.85
    AnchorTagHelper
    0.85
     грн
    0.84
     titolata
    0.84
    Lähteet
    0.84
    Activations Density 0.095%

    No Known Activations