© 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. 3-GEMMASCOPE-RES-16K
    6. 10526
    Prev
    Next
    INDEX
    Explanations

    mentions of "they" or "these" in various 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
    WithIOException
    -0.69
     Савезне
    -0.61
     stupid
    -0.55
     يتيمه
    -0.54
    ין
    -0.52
     linkovi
    -0.52
    好多
    -0.51
    L
    -0.51
    holdt
    -0.50
     silly
    -0.49
    POSITIVE LOGITS
     they
    1.20
    They
    1.08
     They
    1.08
     THEY
    1.05
     themselves
    1.05
    THEY
    1.04
    they
    1.03
    Они
    1.03
     their
    1.01
    Their
    0.99
    Activations Density 0.140%

    No Known Activations