© 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. 3-GEMMASCOPE-RES-16K
    11. 6314
    Prev
    Next
    INDEX
    Explanations

    words related to processes, actions, and instructions in technical or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carlin
    -0.98
     Sis
    -0.90
     latter
    -0.85
     Bader
    -0.82
     Cowan
    -0.80
     restTemplate
    -0.79
    nsic
    -0.77
    多い
    -0.76
    enchymal
    -0.76
    kates
    -0.73
    POSITIVE LOGITS
    ing
    2.66
    ING
    1.87
    izing
    0.99
    ة
    0.97
    ingh
    0.95
    ating
    0.94
    ingi
    0.86
     Pozna
    0.84
    ingan
    0.83
    ging
    0.82
    Activations Density 0.497%

    No Known Activations