© 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. 84992
    Prev
    Next
    INDEX
    Explanations

    references to paganism and related terms

    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
    <bos>
    -0.68
     Christensen
    -0.40
     forças
    -0.38
     ahli
    -0.37
    ||}
    -0.37
    Autowired
    -0.36
     kimia
    -0.36
     Informações
    -0.35
     Hilfe
    -0.35
     Suiza
    -0.35
    POSITIVE LOGITS
     Pag
    1.25
     pag
    1.15
    Pag
    1.09
     PAG
    1.09
    PAG
    1.03
    Paginator
    1.02
     Pagan
    0.96
    pag
    0.92
    paginator
    0.89
     Page
    0.88
    Activations Density 0.005%

    No Known Activations