© 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. 5-GEMMASCOPE-RES-16K
    11. 3280
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rima
    -0.74
     Devan
    -0.70
    UCH
    -0.67
    iVar
    -0.66
     Ellen
    -0.64
     Lom
    -0.64
     Velas
    -0.64
    rique
    -0.64
    thold
    -0.62
     Mura
    -0.61
    POSITIVE LOGITS
    Datuak
    1.08
    Portail
    1.01
    Tembelea
    0.95
     Portail
    0.92
    antaranya
    0.88
     sää
    0.83
     Paglinawan
    0.78
     Pallas
    0.77
     religieuses
    0.77
     bezeichneter
    0.76
    Activations Density 2.408%

    No Known Activations