© 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 EvalsExportsAPI 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. 15592
    Prev
    Next
    INDEX
    Explanations

    references to deserving or worthy treatment or recognition

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

    what is deserved

    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
     Marín
    -0.42
     $\
    -0.35
     principal
    -0.34
    i
    -0.33
     ghosts
    -0.33
     indios
    -0.33
     fold
    -0.33
     Gemeinde
    -0.32
     liens
    -0.32
    ヤー
    -0.32
    POSITIVE LOGITS
     deserve
    1.19
    deserved
    1.10
     deserves
    1.09
     deserved
    1.08
    extAlignment
    1.01
     deserving
    0.90
     незавершена
    0.85
     estekak
    0.83
     الحره
    0.80
     mérit
    0.80
    Activations Density 0.011%

    No Known Activations