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. 3-GEMMASCOPE-RES-16K
    6. 6097
    Prev
    Next
    INDEX
    Explanations

    terms related to banking and the automotive industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MongoClient
    -0.70
    nosaurus
    -0.70
    칙
    -0.69
     EXPERIMENT
    -0.69
     ruf
    -0.69
    τή
    -0.67
     Walkover
    -0.66
     Psychologist
    -0.65
    avax
    -0.65
    ransition
    -0.64
    POSITIVE LOGITS
     gaming
    1.05
     automotive
    1.05
     imaging
    0.96
     robotics
    0.94
     banking
    0.94
     footwear
    0.94
     Gaming
    0.93
     messaging
    0.93
    Gaming
    0.92
     manufacturing
    0.92
    Activations Density 0.130%

    No Known Activations