© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8843
    Prev
    Next
    INDEX
    Explanations

    elements related to academic or research analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cu
    -0.96
    Cu
    -0.92
     Coffey
    -0.83
     CU
    -0.74
     Gloucestershire
    -0.73
     Copper
    -0.72
     Avatar
    -0.71
     Cup
    -0.71
     Giri
    -0.70
    Cup
    -0.69
    POSITIVE LOGITS
     PLUG
    1.03
    Plugin
    1.01
     plugin
    1.00
     Plugin
    0.97
    plugin
    0.89
     plugins
    0.88
    PLUGIN
    0.84
     Plugins
    0.81
    Plugins
    0.79
    插件
    0.79
    Activations Density 1.835%

    No Known Activations