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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 82203
    Prev
    Next
    INDEX
    Explanations

    references to comparative or contrasting ideas, particularly those structured around "one" versus "the other."

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

    on one hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.65
    MigrationBuilder
    -0.63
    enumi
    -0.56
     Administrativna
    -0.56
    enumii
    -0.55
    Personendaten
    -0.55
     للاسماء
    -0.51
     Савезне
    -0.50
    thâu
    -0.50
     Italijanski
    -0.50
    POSITIVE LOGITS
     einerseits
    1.20
    一方面
    1.12
     andererseits
    0.86
     on
    0.83
    另一方面
    0.82
    一方
    0.77
    一边
    0.76
     sisi
    0.68
    一方で
    0.67
    一邊
    0.66
    Activations Density 0.048%

    No Known Activations