Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 15075
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific and academic analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cllr
    -0.55
     Cllr
    -0.54
     poética
    -0.52
    thâu
    -0.52
     propOrder
    -0.51
     автора
    -0.51
     blessés
    -0.51
    這位
    -0.50
     filosó
    -0.49
    这位
    -0.49
    POSITIVE LOGITS
    KommentareTeilen
    1.01
     autorytatywna
    0.81
    mybatisplus
    0.80
    发表于
    0.75
     utafitiHapana
    0.74
     ddelweddau
    0.73
    +:+
    0.68
     متعلقه
    0.68
    出版年
    0.65
     baseball
    0.65
    Activations Density 1.949%

    No Known Activations