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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 1347
    Prev
    Next
    INDEX
    Explanations

    various grammatical structures and relationships in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddHtmlAttribute
    -0.62
    abestanden
    -0.60
     ویکی‌پدی
    -0.59
     препратки
    -0.56
     ſta
    -0.55
     שוליים
    -0.53
     فريبيس
    -0.52
    IsMutable
    -0.52
     surla
    -0.51
     myſelf
    -0.51
    POSITIVE LOGITS
     derives
    0.65
     wynika
    0.58
     derive
    0.57
     derived
    0.56
     يتيمه
    0.52
     deriving
    0.49
     korzyst
    0.48
    derive
    0.48
     profitieren
    0.47
    derived
    0.44
    Activations Density 0.147%

    No Known Activations