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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 16380
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.69
    ніципа
    -0.66
    kháu
    -0.64
    omeness
    -0.64
     препратки
    -0.61
    tanleria
    -0.60
    RenderAtEndOf
    -0.59
     مفص
    -0.59
    archiviato
    -0.59
     مرئيه
    -0.58
    POSITIVE LOGITS
    MessageTagHelper
    0.69
     للاسماء
    0.66
    ViewFeatures
    0.64
    ReusableCell
    0.57
     listening
    0.57
     CreateTagHelper
    0.56
     hitch
    0.51
     gouverneur
    0.50
     argento
    0.50
    LabelTagHelper
    0.50
    Activations Density 0.021%

    No Known Activations