© 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. 20-GEMMASCOPE-RES-131K
    11. 9829
    Prev
    Next
    INDEX
    Explanations

    references to couples and the dynamics of their relationships

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

    couple relationship states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     X
    -0.41
     I
    -0.36
     this
    -0.35
     Wart
    -0.35
     always
    -0.35
     my
    -0.35
     Fisk
    -0.34
     unmarked
    -0.34
     R
    -0.34
    Hyd
    -0.33
    POSITIVE LOGITS
    Couple
    1.30
     Couple
    1.28
    couple
    1.26
     couple
    1.21
     couples
    1.20
     Couples
    1.17
    couples
    1.09
     coppia
    1.04
    parsedMessage
    0.99
    ouple
    0.98
    Activations Density 0.005%

    No Known Activations