© 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 - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13828
    Prev
    Next
    INDEX
    Explanations

    formatted data structures or code snippets related to regions and codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.64
     [];
    -0.60
     pleaf
    -0.60
    ".
    -0.59
     thofe
    -0.56
     feveral
    -0.55
    ching
    -0.54
     itſelf
    -0.54
    []
    -0.54
     Nai
    -0.52
    POSITIVE LOGITS
    SequentialGroup
    0.65
    JspWriter
    0.64
    Koordinaten
    0.63
    principalColumn
    0.62
    findpost
    0.61
    niająca
    0.61
    DataAnnotations
    0.60
     OMITTED
    0.59
    SourceChecksum
    0.59
     nó
    0.55
    Activations Density 0.909%

    No Known Activations