© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 933
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific and medical research complexities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "Complex" or "complexity"

    np_acts-logits-general · gemini-2.0-flash

    complex and difficult

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     يتيمه
    -0.49
    fromCharCode
    -0.44
    RegressionTest
    -0.41
     ventr
    -0.41
    РЭ
    -0.40
    lorus
    -0.39
    inence
    -0.39
    picuous
    -0.38
    𝟸
    -0.38
    StoryboardSegue
    -0.37
    POSITIVE LOGITS
     complexities
    1.29
     complexity
    1.23
     complex
    1.21
     complicated
    1.09
     complexo
    1.02
     compleja
    1.02
     complejidad
    1.01
    complex
    1.00
    复杂
    1.00
     complejo
    1.00
    Activations Density 0.986%

    No Known Activations