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. 2-GEMMASCOPE-RES-16K
    6. 4267
    Prev
    Next
    INDEX
    Explanations

    prepositions related to cause, manner, or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -0.87
     iſt
    -0.77
     itſelf
    -0.76
     Tacitus
    -0.75
     ſeveral
    -0.73
    Vea
    -0.73
     pleaſure
    -0.73
     Majefty
    -0.72
     Theſe
    -0.71
     ISTAT
    -0.71
    POSITIVE LOGITS
     by
    1.12
     por
    1.09
     pelo
    1.05
     pela
    1.03
     par
    0.99
     pelos
    0.98
     pelas
    0.94
     By
    0.92
     przez
    0.89
     durch
    0.87
    Activations Density 0.030%

    No Known Activations