© 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. 5-GEMMASCOPE-RES-16K
    6. 6553
    Prev
    Next
    INDEX
    Explanations

    SQL keywords and functions related to grouping and ordering data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.73
    PMailer
    -0.66
    AccessorTable
    -0.59
     للاسماء
    -0.54
     fol
    -0.54
     Fol
    -0.54
    MemoryWarning
    -0.53
    sitis
    -0.53
    rais
    -0.52
     doGet
    -0.51
    POSITIVE LOGITS
    groupby
    0.86
     câte
    0.68
    modelBuilder
    0.64
    IsContent
    0.64
     awk
    0.57
     mariée
    0.57
     Roskov
    0.55
     marié
    0.55
    wakilan
    0.54
    UseVisualStyle
    0.54
    Activations Density 0.344%

    No Known Activations