© 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. 40-GEMMASCOPE-RES-16K
    11. 6130
    Prev
    Next
    INDEX
    Explanations

    references to moral judgments and ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     técn
    -0.68
     dévelo
    -0.61
     différente
    -0.60
     négatif
    -0.54
     dangereux
    -0.52
     rempliss
    -0.52
     mauva
    -0.52
     différent
    -0.51
     veldig
    -0.50
    guiente
    -0.50
    POSITIVE LOGITS
     forthwith
    0.88
     sundry
    0.85
     aforesaid
    0.84
    倘
    0.82
     pertinent
    0.79
    withstanding
    0.78
     elucid
    0.78
     concomitant
    0.76
     requisite
    0.76
     pertaining
    0.76
    Activations Density 2.228%

    No Known Activations