© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8906
    Prev
    Next
    INDEX
    Explanations

    references to object-oriented concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forChild
    -0.53
     onCancelled
    -0.52
     noDo
    -0.51
    sidemargin
    -0.49
    hyrchwyd
    -0.49
    IndentedString
    -0.48
    WebVitals
    -0.47
     незавершена
    -0.47
    󠁣
    -0.47
     pinulongan
    -0.46
    POSITIVE LOGITS
     obj
    0.59
     lesson
    0.54
     недвижимости
    0.52
    lesson
    0.52
     localObject
    0.49
     Oriented
    0.47
     Object
    0.46
     Obj
    0.45
     OBJ
    0.45
    oriented
    0.44
    Activations Density 0.273%

    No Known Activations