© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1233
    Prev
    Next
    INDEX
    Explanations

    conditional phrases, especially those involving "if" and "whether."

    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
    poto
    -0.57
    rited
    -0.56
     kotor
    -0.54
     JpaRepository
    -0.54
     mandar
    -0.53
    #
    -0.52
     "..\..\
    -0.51
    érez
    -0.51
     maire
    -0.51
    inary
    -0.50
    POSITIVE LOGITS
     فريبيس
    0.81
     المعيارى
    0.76
     IBOutlet
    0.67
    jalá
    0.62
    URLException
    0.60
    UrlResolution
    0.57
    djangoproject
    0.56
    assertIn
    0.56
    utnant
    0.56
     defaultstate
    0.55
    Activations Density 0.106%

    No Known Activations