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. 0-GEMMASCOPE-RES-16K
    6. 6220
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "these."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    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
    -0.94
     ARXIV
    -0.92
     photolibrary
    -0.87
     Efq
    -0.85
     raiſ
    -0.80
     defStyle
    -0.79
     Cæsar
    -0.78
     itſelf
    -0.78
     fevere
    -0.77
     ioe
    -0.75
    POSITIVE LOGITS
     these
    3.94
    these
    3.31
    These
    3.03
     These
    3.00
     THESE
    2.81
     estos
    2.20
     this
    2.18
     queste
    2.17
    这些
    2.13
    這些
    2.04
    Activations Density 0.110%

    No Known Activations