© 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. 6-GEMMASCOPE-RES-16K
    6. 5994
    Prev
    Next
    INDEX
    Explanations

    documentation-related formatting and code annotations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.77
    Spoljašnje
    -0.75
    oredCriteria
    -0.67
    IsContent
    -0.65
    borderRadius
    -0.64
    SharedDtor
    -0.64
     Endor
    -0.61
    Mediabestanden
    -0.60
    ENDIAN
    -0.60
    omitempty
    -0.60
    POSITIVE LOGITS
    vue
    1.41
    Vue
    1.12
     Vue
    1.03
     vue
    0.86
    selenium
    0.81
    java
    0.73
    QtWidgets
    0.72
     "..\..\..\
    0.71
    shtml
    0.70
     "..\..\
    0.68
    Activations Density 0.020%

    No Known Activations