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. 5-GEMMASCOPE-RES-16K
    6. 1824
    Prev
    Next
    INDEX
    Explanations

    phrases related to development and planning processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.82
    meteries
    -0.71
    HasAnnotation
    -0.71
    曖昧さ回避
    -0.70
    ThroughAttribute
    -0.66
     /\.(
    -0.66
     متعلقه
    -0.65
    fromnode
    -0.65
    mybatisplus
    -0.65
    NewUrlParser
    -0.64
    POSITIVE LOGITS
     devising
    1.13
     devised
    1.09
    élaboration
    1.05
     crafting
    1.00
     élabor
    0.99
     designing
    0.96
     tailored
    0.95
     formulating
    0.94
     formulate
    0.91
     crafted
    0.90
    Activations Density 0.349%

    No Known Activations