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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3078
    Prev
    Next
    INDEX
    Explanations

    terms related to research methodologies and ethical considerations in scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.89
     Amish
    -0.84
     Haitian
    -0.83
     HIPAA
    -0.81
    checkFor
    -0.81
     Mexicano
    -0.78
     Grecian
    -0.78
     Conſ
    -0.77
     امريكا
    -0.77
     pleaſure
    -0.76
    POSITIVE LOGITS
     Nowadays
    0.87
     Moreover
    0.81
     analysed
    0.80
    #
    0.79
    neighbour
    0.78
    Moreover
    0.78
    Nowadays
    0.77
     skilful
    0.75
    Annexes
    0.75
     (...)
    0.75
    Activations Density 8.185%

    No Known Activations