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. 154
    Prev
    Next
    INDEX
    Explanations

    terms related to server configurations and errors

    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
     InputDecoration
    -0.73
     taches
    -0.73
    ➡
    -0.73
    hhhhhhhh
    -0.71
     piace
    -0.66
    ../../
    -0.66
    InteropServices
    -0.65
    sont
    -0.65
     Alcott
    -0.65
    ligencia
    -0.64
    POSITIVE LOGITS
     servers
    1.50
     Servers
    1.41
     SERVER
    1.39
     Server
    1.37
     server
    1.33
    Servers
    1.28
    SERVER
    1.27
    Server
    1.27
    server
    1.22
     smtplib
    1.17
    Activations Density 0.105%

    No Known Activations