© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 12611
    Prev
    Next
    INDEX
    Explanations

    the term "Bundle" related to programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.88
    EDEFAULT
    -0.80
    PREFERRED
    -0.76
    "])
    -0.75
    "]').
    -0.74
    "]:
    -0.73
     uintptr
    -0.73
    prefixer
    -0.73
    "](
    -0.73
    matchCondition
    -0.73
    POSITIVE LOGITS
    Bundle
    1.43
    ComponentModel
    0.94
    Uri
    0.91
     Uri
    0.73
     Bundle
    0.66
    InstanceState
    0.64
    RequestMapping
    0.63
    WebControls
    0.58
     AttributeSet
    0.55
     argc
    0.55
    Activations Density 0.012%

    No Known Activations