© 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. 7929
    Prev
    Next
    INDEX
    Explanations

    sections of text that are poorly formatted or inconsistent, possibly indicating coding errors or irrelevant information

    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
    Vegeu
    -0.59
     浜
    -0.50
     col
    -0.48
     st
    -0.47
     sub
    -0.47
    Obrázky
    -0.47
    kal
    -0.47
    lag
    -0.45
    ness
    -0.45
    ity
    -0.44
    POSITIVE LOGITS
     referenties
    1.03
    __':
    
    0.83
    __":
    
    0.80
    awtextra
    0.80
    uxxxx
    0.79
     autorytatywna
    0.78
    发表于
    0.77
     estekak
    0.76
    __":
    0.75
     الحره
    0.73
    Activations Density 0.004%

    No Known Activations