© 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. 8409
    Prev
    Next
    INDEX
    Explanations

    terms related to oil exploration contracts and geological studies

    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
     للمعارف
    -0.56
     propOrder
    -0.54
    rungsseite
    -0.48
    🪳
    -0.48
    PerformLayout
    -0.42
     henvisninger
    -0.40
    matchCondition
    -0.39
     miners
    -0.39
     BorderSide
    -0.39
     embalaje
    -0.39
    POSITIVE LOGITS
     offshore
    0.79
    Offshore
    0.61
     Offshore
    0.61
     discoveries
    0.60
     exploration
    0.60
     Shelf
    0.57
    Shelf
    0.55
     acreage
    0.53
    Exploration
    0.53
     discovery
    0.52
    Activations Density 0.321%

    No Known Activations