© 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. 658
    Prev
    Next
    INDEX
    Explanations

    data structure definitions and variable declarations in programming languages

    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
    PhysRev
    -0.39
    Kariera
    -0.32
     хвати
    -0.32
     andet
    -0.31
    смотря
    -0.30
     tertulis
    -0.28
    bkz
    -0.28
     Zerst
    -0.28
     Umfeld
    -0.28
    但却
    -0.28
    POSITIVE LOGITS
     colours
    0.68
     base
    0.62
     default
    0.62
    VIAF
    0.62
     prefixes
    0.61
    ConverterFactory
    0.60
    sidemargin
    0.59
     colors
    0.59
    findpost
    0.58
    msgTypes
    0.57
    Activations Density 0.448%

    No Known Activations