© 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. 4930
    Prev
    Next
    INDEX
    Explanations

    aspects of societal norms and morality in various contexts

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

    historical figures and events

    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
     Majefty
    -0.70
     للاسماء
    -0.62
    +#+
    -0.56
    iffance
    -0.55
    microb
    -0.53
    praia
    -0.53
    <unused79>
    -0.52
    <unused3>
    -0.51
    [@BOS@]
    -0.51
    <pad>
    -0.51
    POSITIVE LOGITS
     historians
    0.41
     historian
    0.41
     historia
    0.37
     UnityEditor
    0.35
     biographer
    0.34
    
    0.34
     historical
    0.33
    hist
    0.32
     gouvern
    0.32
    LookAnd
    0.31
    Activations Density 0.212%

    No Known Activations