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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 126081
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement and enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Ram
    -0.43
     Mank
    -0.42
     caminh
    -0.39
     MPP
    -0.39
     Marg
    -0.38
     Marr
    -0.38
     BM
    -0.37
     Row
    -0.37
     LN
    -0.36
    ₅
    -0.36
    POSITIVE LOGITS
     excite
    1.12
    Excited
    1.11
    excited
    1.05
     excitement
    1.04
     Excited
    1.03
    excitation
    1.02
    Exciting
    1.02
     excit
    0.99
     Exciting
    0.99
     excitation
    0.99
    Activations Density 0.007%

    No Known Activations