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. 25-GEMMASCOPE-RES-16K
    6. 10202
    Prev
    Next
    INDEX
    Explanations

    references to mobile phone-related concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.68
     "..\..\..\
    -0.54
    abestanden
    -0.54
     Mauer
    -0.54
    ########.
    -0.54
     Tahu
    -0.53
    ::::::::
    -0.51
    ytu
    -0.51
    kháu
    -0.51
    fileID
    -0.50
    POSITIVE LOGITS
     SIM
    1.20
     sim
    1.03
    SIM
    0.99
     GSM
    0.97
     prepaid
    0.88
     Sim
    0.87
     cellular
    0.87
     roaming
    0.86
     Vodafone
    0.84
    GSM
    0.83
    Activations Density 0.266%

    No Known Activations