Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6005
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "namespace" and related package definitions in code documents

    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
    TagMode
    -1.04
    Geplaatst
    -1.03
    URLException
    -0.98
    FunctionFlags
    -0.86
    ScopeManager
    -0.79
    enterOuterAlt
    -0.79
     defaultstate
    -0.76
    AddTagHelper
    -0.76
     Drapeau
    -0.75
     Meksiku
    -0.75
    POSITIVE LOGITS
    namespace
    0.92
    ftance
    0.62
     fuper
    0.58
    xspace
    0.58
    ULUM
    0.57
     firſt
    0.56
     Efq
    0.55
     Jefus
    0.55
     againſt
    0.55
    dari
    0.54
    Activations Density 0.050%

    No Known Activations