© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14741
    Prev
    Next
    INDEX
    Explanations

    references to decision-making processes and instructions

    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
     
    -0.94
     A
    -0.86
     his
    -0.84
     a
    -0.84
     R
    -0.83
    his
    -0.82
     B
    -0.78
     O
    -0.78
    my
    -0.78
     S
    -0.77
    POSITIVE LOGITS
    ValueStyle
    1.44
    tagHelperRunner
    1.40
     tartalomajánló
    1.38
     autorytatywna
    1.32
     resourceCulture
    1.30
     EconPapers
    1.30
    TagMode
    1.28
     esternos
    1.28
    bootstrapcdn
    1.28
     iſt
    1.26
    Activations Density 1.181%

    No Known Activations