© 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. 0-GEMMASCOPE-RES-16K
    11. 8249
    Prev
    Next
    INDEX
    Explanations

    references to accumulating or stacking items, particularly in the context of piles or heaps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ABN
    -0.68
     /\.(
    -0.67
     pleaſure
    -0.66
     Majefty
    -0.66
     auffi
    -0.65
     Anſ
    -0.65
    ſelf
    -0.64
     Diſ
    -0.63
    stringValue
    -0.63
    -0.61
    POSITIVE LOGITS
     pile
    4.42
     Pile
    3.63
     piles
    3.63
    pile
    3.52
    Pile
    3.17
     piled
    2.86
     piling
    2.65
     Piles
    2.56
    piles
    2.52
     stack
    2.24
    Activations Density 0.138%

    No Known Activations