© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27429
    Prev
    Next
    INDEX
    Explanations

    instances of the token "<bos>", indicating the beginning of a new segment or section in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical formulas and data specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -0.71
     whilst
    -0.66
    cektir
    -0.65
    Whilst
    -0.65
     beliau
    -0.64
     ایشان
    -0.63
     please
    -0.58
    luß
    -0.58
     skall
    -0.57
    Figure
    -0.56
    POSITIVE LOGITS
     disambiguazione
    0.79
     ‘‘
    0.77
    Viitteet
    0.73
    SpringRunner
    0.71
    PhysRev
    0.71
    awaiter
    0.71
     spokeswoman
    0.70
    URLException
    0.70
     مرئيه
    0.69
     ifølge
    0.69
    Activations Density 0.063%

    No Known Activations