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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1660
    Prev
    Next
    INDEX
    Explanations

    technical terms related to processes, equipment, and environmental conditions in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.95
    OrWhiteSpace
    -0.77
     Theſe
    -0.74
    mybatisplus
    -0.72
     ouvriers
    -0.69
     Monfieur
    -0.69
     travailleurs
    -0.68
     $_"
    -0.67
     imageName
    -0.66
     skb
    -0.66
    POSITIVE LOGITS
    Gemeinden
    0.49
    AnimationsModule
    0.41
    Handlung
    0.41
     nahilalakip
    0.39
    afficheront
    0.38
    jface
    0.38
    Einzelnachweise
    0.38
    نگار
    0.38
     FSA
    0.38
    بوابة
    0.36
    Activations Density 3.548%

    No Known Activations