© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 10363
    Prev
    Next
    INDEX
    Explanations

    usage of the "with" statement in code, particularly in context of resource management and context managers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ApiModel
    -0.69
    laston
    -0.67
    Datuak
    -0.65
     transfieras
    -0.64
     GMA
    -0.63
     Scalars
    -0.61
     Calla
    -0.60
     manuten
    -0.60
    Kama
    -0.59
    MessageDigest
    -0.59
    POSITIVE LOGITS
    WriteBarrier
    0.68
    ContentAsync
    0.63
    mybatisplus
    0.57
    riwal
    0.57
    忑
    0.57
    الدراسه
    0.56
     egyszer
    0.54
    dorff
    0.53
    وسط
    0.52
     utafiti
    0.52
    Activations Density 0.053%

    No Known Activations