© 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. 34-GEMMASCOPE-RES-16K
    11. 15000
    Prev
    Next
    INDEX
    Explanations

    references to names and statistics within a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feroit
    -0.73
    webElementXpaths
    -0.72
     saveiro
    -0.71
    AndEndTag
    -0.67
     vixion
    -0.66
     MainAxisSize
    -0.65
     auroit
    -0.63
    aronder
    -0.62
     spørsmål
    -0.62
     étoient
    -0.60
    POSITIVE LOGITS
     desi
    0.40
    ̵
    0.39
     gyhoeddwyd
    0.37
     messa
    0.37
    こち
    0.36
     fo
    0.36
     seco
    0.35
    ograp
    0.35
     sayin
    0.35
     separa
    0.35
    Activations Density 0.332%

    No Known Activations