© 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. 18-GEMMASCOPE-RES-16K
    11. 15685
    Prev
    Next
    INDEX
    Explanations

    statements regarding differences and comparisons between entities or concepts

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

    Focuses on distinctions and dissimilarities

    np_acts-logits-general · gemini-2.0-flash

    difference and differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    liesslich
    -0.58
    >//
    -0.52
    ließlich
    -0.45
    migrationBuilder
    -0.44
    atellite
    -0.44
    cooperative
    -0.44
     Thad
    -0.43
    례
    -0.43
    uchungen
    -0.43
    quetas
    -0.42
    POSITIVE LOGITS
     difference
    3.74
     differences
    3.30
    difference
    3.27
     Difference
    3.20
    Difference
    3.13
     Differences
    3.06
    Differences
    2.94
    differences
    2.84
     différence
    2.83
     DIFFERENCE
    2.83
    Activations Density 1.071%

    No Known Activations