© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 456
    Prev
    Next
    INDEX
    Explanations

    specific terms related to science fiction literature and discussions of significant contributions within that genre

    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
     rodillas
    -1.18
     colgante
    -1.12
     fieltro
    -1.11
     plateado
    -1.11
     gruesa
    -1.08
     terciopelo
    -1.06
     desierto
    -1.03
    pecabe
    -1.02
     Económica
    -1.00
     británico
    -0.99
    POSITIVE LOGITS
     seta
    0.82
     cag
    0.79
     travis
    0.76
     illumin
    0.75
     precip
    0.75
     relu
    0.74
     medusa
    0.74
     impro
    0.74
     inv
    0.74
     pizz
    0.73
    Activations Density 0.049%

    No Known Activations