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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12822
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain types of contextual references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     描
    -0.41
     sacra
    -0.41
    so
    -0.41
     Stair
    -0.40
     Molière
    -0.40
     ас
    -0.40
    ulieren
    -0.39
     đến
    -0.39
    ண
    -0.39
    wo
    -0.39
    POSITIVE LOGITS
    NameInMap
    0.84
    complexContent
    0.70
    enumii
    0.70
     cherchés
    0.70
     >=",
    0.70
    contentLoaded
    0.70
    SourceChecksum
    0.69
     Савезне
    0.67
     Paglinawan
    0.67
    хьтан
    0.66
    Activations Density 0.211%

    No Known Activations