© 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. 11886
    Prev
    Next
    INDEX
    Explanations

    concepts related to asynchronous tasks and error handling in programming

    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
     tenuta
    -0.58
    seamnă
    -0.55
    footnote
    -0.49
    Distinctions
    -0.49
    Bienvenue
    -0.48
     Provisional
    -0.47
    AppSettings
    -0.47
    thenia
    -0.47
    yecek
    -0.47
     Ked
    -0.47
    POSITIVE LOGITS
    iVar
    2.31
     iVar
    1.23
    fVar
    1.11
    ScopeManager
    0.93
    ViewFeatures
    0.88
    iLocal
    0.88
    vVar
    0.85
    bParam
    0.83
    NonNull
    0.80
    EndContext
    0.79
    Activations Density 0.014%

    No Known Activations