Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15942
    Prev
    Next
    INDEX
    Explanations

    technical terms and designations related to studies and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Belén
    -0.57
    存于互联网档案馆
    -0.55
    NameInMap
    -0.55
    ômico
    -0.51
     Florentine
    -0.51
     Socorro
    -0.50
    roek
    -0.49
     Orrell
    -0.48
    EndProject
    -0.48
     Rosh
    -0.48
    POSITIVE LOGITS
    EA
    0.75
    UA
    0.73
    NA
    0.73
    XA
    0.73
    MSA
    0.72
    LLA
    0.71
    TSA
    0.70
    ua
    0.70
     aVar
    0.70
    da
    0.69
    Activations Density 0.352%

    No Known Activations