© 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. 0-GEMMASCOPE-RES-16K
    11. 8759
    Prev
    Next
    INDEX
    Explanations

    phrases that signal intention or purpose in a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.72
    ſelves
    -0.67
    ſelf
    -0.67
     Monfieur
    -0.66
     itſelf
    -0.66
    yntaxException
    -0.63
     Anſ
    -0.63
     Jefus
    -0.63
    ientôt
    -0.63
    ècie
    -0.63
    POSITIVE LOGITS
    SPATH
    0.58
     plais
    0.54
    WebVitals
    0.54
    WebServlet
    0.53
    MSI
    0.52
     HasFactory
    0.52
     actually
    0.51
    saraba
    0.51
    ‌تر
    0.51
     []:
    0.50
    Activations Density 0.316%

    No Known Activations