© 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. 0-GEMMASCOPE-RES-16K
    6. 10021
    Prev
    Next
    INDEX
    Explanations

    terms related to mining and resource extraction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    basicConfig
    -0.54
    Архівовано
    -0.52
     ویکی‌پدی
    -0.51
    下载附件
    -0.50
     amitié
    -0.49
    StoryboardSegue
    -0.48
    RenderAtEndOf
    -0.48
     psicológico
    -0.47
     NSCoder
    -0.45
     prière
    -0.42
    POSITIVE LOGITS
     mining
    0.72
     Metall
    0.66
     ceramic
    0.61
     furnace
    0.59
     miners
    0.59
     miner
    0.59
     Mining
    0.58
     Ceramic
    0.58
     metallurgical
    0.58
     metal
    0.56
    Activations Density 1.839%

    No Known Activations