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. 4299
    Prev
    Next
    INDEX
    Explanations

    references to political exploitation and natural resources in historical contexts

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

    natural resources and resource allocation

    np_acts-logits-general · gemini-2.0-flash

    natural resources and treasure

    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
    ValueStyle
    -0.84
     ویکی‌پدیا
    -0.84
    DeleteBehavior
    -0.73
    ConstraintMaker
    -0.66
     Riproduzione
    -0.66
     estimés
    -0.61
     PARSER
    -0.59
    :✨
    -0.59
    assertRaises
    -0.59
    matchCondition
    -0.58
    POSITIVE LOGITS
     resources
    1.97
    resources
    1.63
     Resources
    1.51
    Resources
    1.43
     resource
    1.38
     RESOURCES
    1.37
     ressources
    1.36
     recursos
    1.31
    资源
    1.22
     assets
    1.22
    Activations Density 0.228%

    No Known Activations