Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 5731
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing deficiencies or shortages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.82
    ]='\
    -0.61
    Portail
    -0.60
    oubliez
    -0.55
    //{
    
    -0.55
    ServletException
    -0.55
    LEGGI
    -0.55
     mergeFrom
    -0.55
     שוליים
    -0.54
    ://$
    -0.52
    POSITIVE LOGITS
    luster
    1.11
    lustre
    0.97
    ada
    0.96
     luster
    0.88
     lustre
    0.83
    ADA
    0.78
     thereof
    0.72
    ustre
    0.66
    ey
    0.64
    adas
    0.61
    Activations Density 0.159%

    No Known Activations