© 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. 16-GEMMASCOPE-RES-16K
    6. 7851
    Prev
    Next
    INDEX
    Explanations

    patterns related to data structures and indexing in programming languages

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

    Indexing or slicing operations in code

    np_acts-logits-general · gemini-2.0-flash

    code constructs followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )))),
    -0.79
    rawDesc
    -0.78
    )"),
    -0.77
    }}}}
    -0.77
    '))
    
    -0.75
    RegistryLite
    -0.75
    principalTable
    -0.75
    ")){
    
    -0.73
    '):
    
    -0.69
    CloseOperation
    -0.68
    POSITIVE LOGITS
    DataAnnotations
    0.60
    ,
    0.55
     sobra
    0.49
    以外にも
    0.47
     antaranya
    0.47
    DockStyle
    0.46
    หวัด
    0.46
     coppia
    0.45
     ingår
    0.45
    UpInside
    0.45
    Activations Density 0.481%

    No Known Activations