© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15517
    Prev
    Next
    INDEX
    Explanations

    advanced scientific methods and their applications in research

    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
    istoitu
    -0.59
     يتيمه
    -0.57
     Vorlage
    -0.50
    Rcpp
    -0.50
    ecimento
    -0.48
     refusé
    -0.48
     raccomand
    -0.47
    Vorlage
    -0.46
    pruch
    -0.46
    tagena
    -0.45
    POSITIVE LOGITS
     study
    2.20
     studying
    2.13
     analysis
    1.97
     analyzing
    1.94
     investigating
    1.91
     analysing
    1.89
     investigation
    1.89
     investigate
    1.86
    study
    1.86
     analyze
    1.83
    Activations Density 1.936%

    No Known Activations