© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7300
    Prev
    Next
    INDEX
    Explanations

    references to characters and elements from mythological and fantastical narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Monfieur
    -0.84
     myſelf
    -0.72
     himſelf
    -0.71
     Jefus
    -0.71
    ſelf
    -0.71
     itſelf
    -0.69
     Anſ
    -0.68
     Houſe
    -0.67
     يتيمه
    -0.67
     Majefty
    -0.66
    POSITIVE LOGITS
    PMailer
    0.41
     Latin
    0.38
     Latein
    0.37
     romanos
    0.36
    ローマ
    0.36
     latein
    0.36
     liée
    0.35
     sièges
    0.35
     destinée
    0.35
     smtplib
    0.34
    Activations Density 0.074%

    No Known Activations