© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 6269
    Prev
    Next
    INDEX
    Explanations

    references to articles, blogs, or informational summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.64
     this
    -0.57
     takiej
    -0.51
     solcher
    -0.51
     solche
    -0.49
     solchen
    -0.49
     этого
    -0.48
     daarvan
    -0.48
    Демографія
    -0.48
     sådan
    -0.46
    POSITIVE LOGITS
     alone
    0.91
     ALONE
    0.74
    alone
    0.73
     Alone
    0.59
     👆
    0.57
     particulier
    0.56
     particular
    0.56
     specifically
    0.55
    homonymie
    0.54
    particular
    0.53
    Activations Density 0.595%

    No Known Activations