© 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. 8355
    Prev
    Next
    INDEX
    Explanations

    references to coding errors or issues in software development

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

    "I have" or sentence beginnings

    np_acts-logits-general · gemini-2.0-flash

    I have; solution

    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
     whatnot
    -1.06
     MainAxisSize
    -1.05
     lenker
    -1.02
    albeit
    -0.98
     saurait
    -0.96
     Asimismo
    -0.95
    Rüyada
    -0.93
    Hentet
    -0.91
     tantôt
    -0.90
     albeit
    -0.89
    POSITIVE LOGITS
     begin
    0.68
     don
    0.56
     like
    0.52
     maybe
    0.50
     Because
    0.50
     began
    0.49
     especial
    0.49
     can
    0.49
     want
    0.49
     is
    0.48
    Activations Density 0.885%

    No Known Activations