© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 16093
    Prev
    Next
    INDEX
    Explanations

    references to versions and copyright details of software

    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
    <eos>
    -0.73
     
    -0.59
    ↵
    -0.54
    ↵↵
    -0.54
     i
    -0.52
     A
    -0.50
      
    -0.46
     d
    -0.46
     deel
    -0.46
    ...
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    1.24
     ExecuteAsync
    1.14
    Datuak
    1.10
    NUMX
    1.09
    BibitemShut
    1.08
     للاسماء
    1.07
     Chwiliwch
    1.07
     ProtoMessage
    1.06
    WriteTagHelper
    1.04
    writeFieldEnd
    1.04
    Activations Density 0.020%

    No Known Activations