© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10876
    Prev
    Next
    INDEX
    Explanations

    elements related to graph nodes and edges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.62
     Paglinawan
    -1.59
    GEBURTSDATUM
    -1.40
     Roskov
    -1.33
    OGND
    -1.32
     Савезне
    -1.32
     kaarangay
    -1.31
    contentLoaded
    -1.27
     autorytatywna
    -1.26
    ArrowToggle
    -1.25
    POSITIVE LOGITS
     أيضاً
    0.51
    ,
    0.46
     ہی
    0.46
    .
    0.44
      
    0.42
     likewise
    0.40
     (
    0.40
    <strong>
    0.39
    ↵↵
    0.39
     medes
    0.39
    Activations Density 20.064%

    No Known Activations