© 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. 5-GEMMASCOPE-RES-16K
    11. 8189
    Prev
    Next
    INDEX
    Explanations

    references to "the" and "first" indicating emphasis on specific items or ideas

    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
    MigrationBuilder
    -0.60
     voeten
    -0.54
    TintMode
    -0.52
     thither
    -0.51
     Agreg
    -0.51
     recentemente
    -0.51
     McInt
    -0.50
     levanta
    -0.50
    Torn
    -0.49
     uniqlo
    -0.49
    POSITIVE LOGITS
    ที่สุด
    0.66
     best
    0.65
    édrale
    0.65
    enumi
    0.64
     LoggerFactory
    0.64
    annica
    0.63
     inilah
    0.63
     itulah
    0.62
     fieldNum
    0.60
    EDEFAULT
    0.59
    Activations Density 0.260%

    No Known Activations