© 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. 9-GEMMASCOPE-RES-131K
    11. 117014
    Prev
    Next
    INDEX
    Explanations

    words with the root "un" or variations related to negation or absence

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

    ung, unary, or ump prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.54
    Role
    -0.53
    Portail
    -0.52
    createClass
    -0.51
    archiviato
    -0.50
    jMenuItem
    -0.49
    #)
    -0.47
    Saman
    -0.47
    Death
    -0.46
    Fig
    -0.45
    POSITIVE LOGITS
     ung
    1.96
     Ung
    1.73
    Ung
    1.45
     ungu
    0.98
     Unger
    0.98
     nong
    0.81
     unc
    0.72
     unge
    0.71
     Ong
    0.59
     unga
    0.59
    Activations Density 0.013%

    No Known Activations