© 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. 2-GEMMASCOPE-RES-16K
    6. 15373
    Prev
    Next
    INDEX
    Explanations

    words related to the term "do" in various contexts, particularly in relation to commands or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEncoder
    -0.89
     StringVar
    -0.85
    enciais
    -0.82
     itſelf
    -0.81
     springfox
    -0.79
    SpringRunner
    -0.79
     ISNI
    -0.77
    antenimiento
    -0.77
     Theſe
    -0.76
     Dyck
    -0.76
    POSITIVE LOGITS
     до
    2.72
    До
    1.80
     До
    1.58
     ДО
    1.41
    до
    1.40
     hasta
    1.14
     تا
    1.05
     עד
    1.03
     till
    1.02
    Hasta
    1.01
    Activations Density 0.027%

    No Known Activations