Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10298
    Prev
    Next
    INDEX
    Explanations

    references to data structures or indices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "index" and related terms

    np_acts-logits-general · gemini-2.0-flash

    index, programming, listings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.80
     élector
    -0.62
    ณี
    -0.53
    هور
    -0.50
     sân
    -0.49
    hab
    -0.49
     Alamofire
    -0.49
    JECT
    -0.48
    Искәрмәләр
    -0.48
    DrawerToggle
    -0.47
    POSITIVE LOGITS
    |[]
    0.82
     disambiguazione
    0.82
     typelib
    0.79
     getIndex
    0.79
     finger
    0.72
     refraction
    0.71
    
    0.69
     fingers
    0.66
     Finger
    0.64
     незавершена
    0.64
    Activations Density 0.131%

    No Known Activations