© 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. 34-GEMMASCOPE-RES-16K
    11. 11172
    Prev
    Next
    INDEX
    Explanations

    references to influential figures in architecture and design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.44
     đang
    -0.43
    Autoritní
    -0.43
     momentan
    -0.42
    Jegyzetek
    -0.34
    目前
    -0.34
    既然
    -0.34
     trendy
    -0.34
     referenties
    -0.33
     currently
    -0.33
    POSITIVE LOGITS
     tirelessly
    0.82
     zawsze
    0.80
     always
    0.80
     vždy
    0.79
     innumerable
    0.75
     lifelong
    0.74
     predeceased
    0.73
     altijd
    0.73
     decades
    0.73
     memorable
    0.72
    Activations Density 0.322%

    No Known Activations