© 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. 9-GEMMASCOPE-RES-16K
    11. 1648
    Prev
    Next
    INDEX
    Explanations

    various types of import statements and references in code snippets, particularly in Android and Java contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.84
    twimg
    -0.53
     černá
    -0.50
    CodeAnalysis
    -0.48
    олові
    -0.48
    皂
    -0.47
    rungsseite
    -0.47
    IndentedString
    -0.47
    mbg
    -0.47
     autonome
    -0.46
    POSITIVE LOGITS
    rxjs
    1.00
    CodeAttribute
    0.85
     resourceCulture
    0.82
    SequentialGroup
    0.76
    mobileqq
    0.76
    HasForeignKey
    0.71
     referenties
    0.65
    msgid
    0.64
    LECTIONS
    0.61
     LiveData
    0.61
    Activations Density 0.012%

    No Known Activations