© 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. 692
    Prev
    Next
    INDEX
    Explanations

    phrases related to announcements and communications regarding events or details

    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
     onCreateView
    -0.57
     StatefulWidget
    -0.56
    يكب
    -0.56
     виправивши
    -0.55
     NKC
    -0.55
    ragalactic
    -0.52
     PON
    -0.50
    boutin
    -0.49
    INSEE
    -0.49
    __]
    -0.49
    POSITIVE LOGITS
     announced
    0.85
     announce
    0.85
     متعلقه
    0.85
     anunciado
    0.84
     anunci
    0.82
     announcing
    0.81
     announces
    0.80
     Announced
    0.75
     anunciar
    0.75
     annoncé
    0.74
    Activations Density 0.238%

    No Known Activations