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. 2722
    Prev
    Next
    INDEX
    Explanations

    events and locations where gatherings or ceremonies are held

    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
     kom
    -0.43
     service
    -0.40
     sign
    -0.40
     tr
    -0.40
    idazole
    -0.39
     index
    -0.39
     متعلقه
    -0.39
    ťaž
    -0.39
    load
    -0.38
    querque
    -0.38
    POSITIVE LOGITS
    sidemargin
    1.00
    IUrlHelper
    0.90
    CppMethod
    0.84
     surla
    0.79
     snippetHide
    0.74
    ":[{
    0.74
    ollectionView
    0.73
     cherchés
    0.71
     оригіналу
    0.70
    expandindo
    0.69
    Activations Density 0.213%

    No Known Activations