© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10593
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or characteristics

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

    Sentences containing "that" or "which."

    np_acts-logits-general · gemini-2.0-flash

    relative clauses or subordinate clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     also
    -0.44
     whose
    -0.42
    ström
    -0.41
     who
    -0.41
     whofe
    -0.40
     Odin
    -0.40
     Crank
    -0.39
     thậm
    -0.38
    lelő
    -0.37
    览
    -0.37
    POSITIVE LOGITS
    fromnode
    0.84
    makeText
    0.83
     للمعارف
    0.82
     transpired
    0.80
     befall
    0.77
    IVEREF
    0.75
     jakie
    0.73
     arise
    0.72
    TagMode
    0.71
     AssemblyTitle
    0.71
    Activations Density 0.295%

    No Known Activations