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. 14-GEMMASCOPE-RES-16K
    6. 6670
    Prev
    Next
    INDEX
    Explanations

    programmer-related terminology and specific data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perfons
    -0.60
     Efq
    -0.58
     intptr
    -0.55
     Jefus
    -0.55
    endphp
    -0.53
    omiast
    -0.52
    ServiceTest
    -0.51
    initializeApp
    -0.51
    secta
    -0.51
     onOptions
    -0.51
    POSITIVE LOGITS
    IUrlHelper
    0.67
    titleMargin
    0.63
    InjectAttribute
    0.59
    RegressionTest
    0.51
    存于互联网档案馆
    0.51
    noopener
    0.50
    orcid
    0.49
    Personendaten
    0.48
     Score
    0.47
    CreateModel
    0.47
    Activations Density 0.626%

    No Known Activations