© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11694
    Prev
    Next
    INDEX
    Explanations

    code-related elements and structures, particularly in programming languages like C++

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.47
    tagHelperRunner
    -0.45
     considérons
    -0.41
    HomeAsUp
    -0.40
     henvisninger
    -0.39
    daille
    -0.38
    FlatAppearance
    -0.37
    
    -0.37
    KommentareTeilen
    -0.36
    Generalized
    -0.35
    POSITIVE LOGITS
     namespace
    1.42
    namespace
    1.20
     Namespace
    1.05
    Namespace
    1.04
     namespaces
    1.02
    NAMESPACE
    0.94
    Namespaces
    0.83
     package
    0.80
    namespaces
    0.79
     ns
    0.75
    Activations Density 0.558%

    No Known Activations