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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12867
    Prev
    Next
    INDEX
    Explanations

    technical terms related to operational systems and equipment functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     EconPapers
    -0.77
     tweaked
    -0.77
     snippetHide
    -0.74
     tweaks
    -0.74
     famously
    -0.73
     maxed
    -0.70
     Sadly
    -0.70
     clunky
    -0.70
     tweaking
    -0.70
    NameInMap
    -0.69
    POSITIVE LOGITS
     skall
    0.89
     shall
    0.75
     muß
    0.75
     convenable
    0.65
    faßt
    0.63
     hereinafter
    0.60
     sufficient
    0.60
     satisfactory
    0.59
     adequate
    0.59
     exigences
    0.59
    Activations Density 1.145%

    No Known Activations