© 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. 22-GEMMASCOPE-RES-16K
    11. 6667
    Prev
    Next
    INDEX
    Explanations

    version numbers and dependency information in a software or data context

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

    Versions (x.x or x.x.x)

    np_acts-logits-general · gemini-2.0-flash

    version numbers

    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
     ir
    -0.53
     l
    -0.48
     kä
    -0.44
     за
    -0.44
    boho
    -0.43
     group
    -0.43
     var
    -0.43
     der
    -0.43
     ange
    -0.42
     assume
    -0.42
    POSITIVE LOGITS
     виправивши
    0.91
     myſelf
    0.86
     itſelf
    0.83
    ագրություններ
    0.82
     EconPapers
    0.79
     Efq
    0.77
      (
    0.77
     themſelves
    0.74
    /*
    0.74
     faſt
    0.74
    Activations Density 0.238%

    No Known Activations