© 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. 5-GEMMASCOPE-RES-16K
    11. 12520
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to programming, particularly in the context of handling events and requests in a web server framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mapStateToProps
    -0.66
    IsContent
    -0.60
     ConstraintSet
    -0.57
    DAI
    -0.55
    tonode
    -0.53
     Pais
    -0.51
    WithMany
    -0.51
    trique
    -0.51
    ूत
    -0.50
    UnifiedTopology
    -0.50
    POSITIVE LOGITS
    pyx
    4.56
    Pyx
    1.75
     <<<<<<<<<<<<<<
    1.19
    jspx
    1.19
    ScopeManager
    1.08
    PYX
    0.97
    ագրություններ
    0.94
     مشين
    0.88
     PyObject
    0.85
    TypedDataSet
    0.84
    Activations Density 0.013%

    No Known Activations