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. 8135
    Prev
    Next
    INDEX
    Explanations

    parameters that indicate quality and functionality in technology products

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

    Followed by nouns (integr, solution, music, puzzle)

    np_acts-logits-general · gemini-2.0-flash

    technical solutions and reliable integration

    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
    oredCriteria
    -0.72
    Personendaten
    -0.68
    Lastly
    -0.57
    πει
    -0.56
     حين
    -0.55
     onOptions
    -0.54
     obstante
    -0.54
     atrocious
    -0.53
     EconPapers
    -0.53
    НОЙ
    -0.52
    POSITIVE LOGITS
    TagMode
    0.66
     Yandex
    0.66
     avto
    0.65
     thematic
    0.64
     analogues
    0.61
     hvil
    0.60
    yandex
    0.60
    )))
    
    0.59
    ContentAsync
    0.57
     analogs
    0.56
    Activations Density 0.116%

    No Known Activations