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. 13-GEMMASCOPE-RES-16K
    6. 465
    Prev
    Next
    INDEX
    Explanations

    terminology related to engineering and technical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical terms and concepts related to polymers and material science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical process terms built with the -ize/-ization/-ising morphology (nominalizations and related verb forms)

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consultato
    -0.64
     брать
    -0.61
    IConfiguration
    -0.56
    SuppressMessage
    -0.56
    KommentareTeilen
    -0.54
     تانيه
    -0.53
     تضيفلها
    -0.53
     يتيمه
    -0.51
    λίου
    -0.51
    OnDelete
    -0.51
    POSITIVE LOGITS
     betweenstory
    0.71
    marshal
    0.67
    AsUp
    0.65
    ing
    0.65
     anuales
    0.61
     stanga
    0.59
     raiſ
    0.59
     tranſ
    0.58
     düzen
    0.56
     dreapta
    0.55
    Activations Density 0.910%

    No Known Activations