© 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. 13-GEMMASCOPE-RES-65K
    11. 58051
    Prev
    Next
    INDEX
    Explanations

    special tokens that indicate the beginning of a sequence or section in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.51
     from
    -0.46
     [
    -0.46
    ('.',
    -0.45
    eri
    -0.45
    <eos>
    -0.44
     Ersten
    -0.44
    ốc
    -0.43
    </i>
    -0.42
      
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    1.52
    Personendaten
    1.12
    SourceChecksum
    1.02
     &___
    1.02
     Roskov
    0.99
    tagext
    0.98
    ftagPool
    0.96
     propOrder
    0.95
    IndentedString
    0.94
     مرئيه
    0.94
    Activations Density 0.014%

    No Known Activations