© 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. 20-GEMMASCOPE-RES-16K
    11. 10939
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, particularly those associated with function definitions and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.45
    erved
    -0.40
     ravens
    -0.40
     postępo
    -0.39
     washes
    -0.38
    fontaine
    -0.38
     pember
    -0.38
    뀐
    -0.38
     Eigen
    -0.38
     pep
    -0.38
    POSITIVE LOGITS
    +#+#
    0.51
    WriteTagHelper
    0.46
    ContentLoaded
    0.42
     ligiloj
    0.41
    ArrowToggle
    0.39
    RuleContext
    0.39
     trattano
    0.39
    enterOuterAlt
    0.37
     createState
    0.37
     &___
    0.37
    Activations Density 0.335%

    No Known Activations