Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2576
    Prev
    Next
    INDEX
    Explanations

    key terms related to mining and pollution regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the extraction of resources from the earth

    np_acts-logits-general · gemini-2.0-flash

    coal and uranium mining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    참고
    -0.57
    िल्ली
    -0.55
    richTextPanel
    -0.54
    SharedDtor
    -0.54
    PyTuple
    -0.54
    ServletException
    -0.53
    kháu
    -0.52
    atouille
    -0.52
    BrowserModule
    -0.51
     mergeFrom
    -0.50
    POSITIVE LOGITS
     mining
    1.87
     mine
    1.84
     mines
    1.76
     mined
    1.61
     Mining
    1.60
     miners
    1.59
     Mine
    1.55
    mining
    1.52
    Mine
    1.48
    Mining
    1.48
    Activations Density 0.206%

    No Known Activations