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. 3878
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or data structures, particularly involving functions and parameters

    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
    IntoConstraints
    -0.91
     Мексичка
    -0.90
     CreateTagHelper
    -0.90
     MainAxisSize
    -0.86
     Administrativna
    -0.82
     propOrder
    -0.82
    GEBURTSDATUM
    -0.80
     viewType
    -0.80
    ViewFeatures
    -0.78
    WindowConstants
    -0.75
    POSITIVE LOGITS
    con
    0.48
     vi
    0.46
    chs
    0.45
    vi
    0.45
     Sta
    0.45
     MERCHANTABILITY
    0.43
    nose
    0.43
    ctic
    0.42
    ξ
    0.42
     بینی
    0.42
    Activations Density 0.532%

    No Known Activations