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. 5887
    Prev
    Next
    INDEX
    Explanations

    expressions of pride and acknowledgment of personal achievements, especially in the context of motherhood and responsibility

    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
    Tembelea
    -0.61
    encodeWith
    -0.59
    +:+
    -0.57
    RSpec
    -0.51
    newcommand
    -0.49
    Erreferentziak
    -0.48
    esm
    -0.46
    UserScript
    -0.46
     noft
    -0.45
    λή
    -0.45
    POSITIVE LOGITS
     Paglinawan
    0.60
    ंदीखरीदारी
    0.57
     acceptez
    0.57
    tagext
    0.57
    ttemberg
    0.57
    StoreMessageInfo
    0.56
     actionMode
    0.55
     viewType
    0.55
    Anyway
    0.55
    Itoa
    0.54
    Activations Density 0.174%

    No Known Activations