© 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. 13233
    Prev
    Next
    INDEX
    Explanations

    questions or statements that express the ability or possibility of doing something

    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
    BibitemShut
    -1.10
     Himo
    -1.10
    devamını
    -0.99
     Audiodateien
    -0.99
    )");
    
    -0.99
    %");
    -0.96
    adget
    -0.95
    ^(@)
    -0.94
    )";
    
    -0.94
     Roskov
    -0.94
    POSITIVE LOGITS
    S
    0.64
    Can
    0.60
    has
    0.59
    can
    0.57
    -
    0.55
    CAN
    0.54
    May
    0.54
    Wil
    0.54
     Can
    0.49
    Has
    0.49
    Activations Density 0.116%

    No Known Activations