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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84343
    Prev
    Next
    INDEX
    Explanations

    references to glutamate and its variants in biochemical contexts

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

    glu, glut, gluc

    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
    ValueStyle
    -0.65
     στιγ
    -0.56
    DetailComponent
    -0.54
    ISupport
    -0.52
    ThroughAttribute
    -0.52
    ResourceId
    -0.50
     للاسماء
    -0.50
    #
    -0.50
    Portail
    -0.47
     beginnetje
    -0.47
    POSITIVE LOGITS
    Glu
    1.02
     Glu
    0.99
    glu
    0.91
    chengladbach
    0.84
     glu
    0.84
     glutamate
    0.81
     gluon
    0.81
     gluta
    0.76
     GoogleFonts
    0.69
    Glue
    0.68
    Activations Density 0.013%

    No Known Activations