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. 11-GEMMASCOPE-RES-16K
    6. 5742
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remind" and its variations, suggesting a focus on themes of memory and reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    easeOut
    -0.82
    chesse
    -0.81
    ंत्री
    -0.76
    SqlClient
    -0.74
    EXPERIMENTAL
    -0.73
    twimg
    -0.73
    +:+
    -0.72
    WEBPACK
    -0.72
     Normdatei
    -0.71
    gebnisse
    -0.70
    POSITIVE LOGITS
     remind
    1.64
     reminder
    1.63
     reminded
    1.57
     reminding
    1.53
    Remind
    1.52
     reminders
    1.52
     Remind
    1.51
     Reminder
    1.46
     Reminders
    1.44
     reminds
    1.44
    Activations Density 0.069%

    No Known Activations