© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 6540
    Prev
    Next
    INDEX
    Explanations

    references to manufacturers and the manufacturing process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orgel
    -0.76
     мәкалә
    -0.74
     Bier
    -0.73
    iedo
    -0.70
     Probes
    -0.70
     Kean
    -0.69
     JComboBox
    -0.69
     faiths
    -0.68
    ｀
    -0.68
     Trello
    -0.68
    POSITIVE LOGITS
     manufacturing
    1.43
     MANUFACT
    1.40
     manufac
    1.39
     manufactures
    1.35
     manufacturers
    1.34
     manufacture
    1.33
     Manufacturing
    1.28
     manufact
    1.27
     manuf
    1.26
     manufactured
    1.26
    Activations Density 0.076%

    No Known Activations