Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8706
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and legal regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.85
     purpoſe
    -0.73
    rungsseite
    -0.70
    ſelves
    -0.68
     ब्रेकडाउन
    -0.67
     ceded
    -0.65
     Houſe
    -0.63
     monographs
    -0.63
     imagui
    -0.63
    Referencie
    -0.63
    POSITIVE LOGITS
     Afterward
    0.67
     afterward
    0.67
     yearly
    0.59
     governmental
    0.55
     beforehand
    0.50
     Yearly
    0.49
     Governmental
    0.49
     oftentimes
    0.48
     gotten
    0.47
     youthful
    0.45
    Activations Density 0.435%

    No Known Activations