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. 2364
    Prev
    Next
    INDEX
    Explanations

    references to diplomatic and international relations

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

    "the" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    specific noun phrases

    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
     Tapatalk
    -0.79
    Erfolge
    -0.57
    Бахар
    -0.52
    ElementException
    -0.51
     touristes
    -0.51
    وأضاف
    -0.50
     propriedade
    -0.50
    jutnya
    -0.50
     GenerationType
    -0.50
     besoins
    -0.49
    POSITIVE LOGITS
     seno
    0.69
     halls
    0.69
     وتسجيلات
    0.68
     ranks
    0.68
     pinulongan
    0.65
     minds
    0.65
     eyes
    0.64
    IUrlHelper
    0.62
     corridors
    0.59
     face
    0.59
    Activations Density 0.319%

    No Known Activations