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

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 2059
    Prev
    Next
    INDEX
    Explanations

    phrases and elements related to programming concepts and code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    existence or presence

    np_acts-logits-general · gemini-2.0-flash

    existence, being, occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.60
    صیلات
    -0.58
    entyfik
    -0.58
     sash
    -0.56
     intracranial
    -0.56
    olite
    -0.56
     ujednoznacz
    -0.54
     polymorph
    -0.53
     للمعارف
    -0.53
     AssemblyCompany
    -0.52
    POSITIVE LOGITS
     there
    1.23
     are
    1.02
     exist
    0.99
     occurs
    0.98
     is
    0.92
     exists
    0.91
     occur
    0.90
     existe
    0.90
    there
    0.89
     υπάρχ
    0.88
    Activations Density 0.046%

    No Known Activations