© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 5259
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations and service quality

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

    pronoun + needed/wants

    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
    Negative Logits
     vertre
    -0.40
     wijze
    -0.37
     überg
    -0.36
     dokonce
    -0.35
     przeprowad
    -0.34
     aanwezig
    -0.33
    الدراسه
    -0.33
     Versuche
    -0.33
     zabaw
    -0.32
    出版年
    -0.32
    POSITIVE LOGITS
     needed
    0.75
    needed
    0.68
     NEEDED
    0.64
     necessary
    0.62
     Needed
    0.61
    Needed
    0.60
     deserved
    0.59
     nødven
    0.56
     required
    0.56
    nexpected
    0.56
    Activations Density 0.014%

    No Known Activations