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. 2-GEMMASCOPE-RES-16K
    6. 15967
    Prev
    Next
    INDEX
    Explanations

    sections related to materials and methods in scientific research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.61
    webElementGuid
    -0.51
    TagHelpers
    -0.49
     cross
    -0.47
     Cross
    -0.47
    änen
    -0.47
    eqn
    -0.45
    薪
    -0.45
     or
    -0.45
    Cross
    -0.44
    POSITIVE LOGITS
    曖昧さ回避
    1.23
     Conclusions
    1.12
    Conclusions
    1.08
    RegressionTest
    1.07
    __":
    
    1.03
    verwijspagina
    1.00
    RODUCTION
    0.99
     disambiguazione
    0.99
    PRNewswire
    0.97
    rungsseite
    0.97
    Activations Density 0.784%

    No Known Activations