© 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. 12417
    Prev
    Next
    INDEX
    Explanations

    instances of inclusion, criteria, and listing related terms

    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
     itſelf
    -1.16
     myſelf
    -1.06
    AndEndTag
    -1.02
     poffible
    -1.00
     raiſ
    -0.97
     uſed
    -0.94
     ſeveral
    -0.94
     purpoſe
    -0.92
    ſelves
    -0.92
     GenerationType
    -0.90
    POSITIVE LOGITS
    :
    0.83
    toEqual
    0.65
     
    0.62
     include
    0.62
     adalah
    0.59
     is
    0.58
     :
    0.55
     a
    0.55
    的是
    0.51
    的就是
    0.49
    Activations Density 0.593%

    No Known Activations