© 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. 7921
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential outcomes and observations in a discussion or analysis context

    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
    DataAnnotations
    -0.69
    TemporalType
    -0.58
    Cyfeiriadau
    -0.56
    Життєпис
    -0.55
    mybatisplus
    -0.55
     ['$
    -0.54
    ViewInit
    -0.54
    GGI
    -0.53
     ElementRef
    -0.53
     ujednoznacz
    -0.52
    POSITIVE LOGITS
     lastly
    0.92
     finally
    0.90
    reszcie
    0.79
     enfin
    0.75
     finalmente
    0.71
     наконец
    0.69
     schließlich
    0.69
     infine
    0.68
     Lastly
    0.67
    Lastly
    0.66
    Activations Density 0.323%

    No Known Activations