© 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. 6683
    Prev
    Next
    INDEX
    Explanations

    JavaScript and jQuery syntax elements used for handling events and AJAX requests

    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
    BufferException
    -0.53
    ProgressHUD
    -0.52
     protoimpl
    -0.51
     Rosalie
    -0.43
     agrí
    -0.42
     fallu
    -0.42
     Allegretto
    -0.42
    addCriterion
    -0.42
    ūsų
    -0.40
    stateMutability
    -0.39
    POSITIVE LOGITS
     onOptions
    0.84
    ManagedBean
    0.76
    DockStyle
    0.76
    出版年
    0.74
     يتيمه
    0.66
    ftagPool
    0.66
    HomeAsUpEnabled
    0.66
     FetchType
    0.64
    UpInside
    0.64
     MaterialApp
    0.64
    Activations Density 0.101%

    No Known Activations