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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12632
    Prev
    Next
    INDEX
    Explanations

    educational qualifications and academic achievements

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

    Graduation honors (cum laude, magna cum laude, summa cum laude)

    np_acts-logits-general · gemini-2.0-flash

    graduation and academic honors

    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
    presente
    -0.47
    Rptr
    -0.47
     new
    -0.47
    Whoever
    -0.45
    дне
    -0.45
    zyw
    -0.45
     whether
    -0.44
     whoever
    -0.43
     reven
    -0.43
    ardless
    -0.43
    POSITIVE LOGITS
     summa
    1.02
     magna
    0.92
     cum
    0.88
     Summa
    0.86
     specializing
    0.81
    magna
    0.79
     Cum
    0.79
     Magna
    0.78
     majoring
    0.76
     specialising
    0.75
    Activations Density 0.105%

    No Known Activations