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. 6-GEMMASCOPE-RES-16K
    6. 382
    Prev
    Next
    INDEX
    Explanations

    references to themes in a programming or application context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldBuilder
    -0.63
    ValueGeneration
    -0.59
    awaiter
    -0.58
    DeleteMapping
    -0.58
    arraycopy
    -0.57
     singly
    -0.57
    WaitGroup
    -0.57
     geografic
    -0.56
    canActivate
    -0.56
    caloosa
    -0.55
    POSITIVE LOGITS
     Theme
    1.99
    Theme
    1.94
    theme
    1.90
     theme
    1.77
    THEME
    1.54
     THEME
    1.49
     Themes
    1.18
     themes
    1.15
     ThemeData
    1.13
    themes
    1.10
    Activations Density 0.014%

    No Known Activations