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. 12-GEMMASCOPE-RES-16K
    6. 803
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of enhancement or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bieber
    -0.78
    itoneum
    -0.77
    nbc
    -0.67
    لكتر
    -0.65
     Mourinho
    -0.65
     Kardashian
    -0.65
    Vicky
    -0.64
     blu
    -0.63
     Beckham
    -0.63
     Nj
    -0.63
    POSITIVE LOGITS
    hancing
    1.19
     supplements
    1.09
     enhancements
    1.07
     enhancement
    1.06
    Enhance
    1.06
     augmentation
    1.04
     supplement
    1.03
     augment
    1.01
     enhance
    1.00
     complements
    0.97
    Activations Density 0.168%

    No Known Activations