© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5399
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational accomplishments and reputations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advancements
    -0.71
     showcased
    -0.69
     somit
    -0.66
     אשר
    -0.66
    自身の
    -0.66
     attire
    -0.64
     showcasing
    -0.63
     captivating
    -0.62
    ]='\
    -0.62
    Upon
    -0.62
    POSITIVE LOGITS
     things
    0.90
     somebody
    0.83
     cosas
    0.82
     stuff
    0.81
     probably
    0.81
     wierd
    0.80
     basically
    0.78
     Надо
    0.78
     Somebody
    0.78
     dingen
    0.77
    Activations Density 2.611%

    No Known Activations