© 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. 21-GEMMASCOPE-RES-16K
    11. 11022
    Prev
    Next
    INDEX
    Explanations

    terms related to website cookie preferences and user consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.60
     ſte
    -0.54
     ſch
    -0.50
     terribly
    -0.50
     ſtill
    -0.50
     abſ
    -0.49
     ſta
    -0.48
     matters
    -0.48
     арен
    -0.47
     ſtand
    -0.47
    POSITIVE LOGITS
    adaptiveStyles
    0.71
    httphttps
    0.59
     comuniques
    0.57
    rungsseite
    0.56
    Referanser
    0.54
    
    0.52
     noDo
    0.52
     lenker
    0.52
    SharedCtor
    0.52
     protoimpl
    0.52
    Activations Density 0.556%

    No Known Activations