© 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. 8134
    Prev
    Next
    INDEX
    Explanations

    phrases related to foundational principles or concepts

    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
     Sweeney
    -0.62
    SUNG
    -0.61
     Donahue
    -0.60
    جرة
    -0.58
     Fle
    -0.57
     Dodson
    -0.56
     Mack
    -0.56
     overras
    -0.56
     Dumont
    -0.55
    nolog
    -0.54
    POSITIVE LOGITS
     basis
    3.13
    basis
    2.98
     Basis
    2.94
    Basis
    2.83
     BASIS
    2.71
     bases
    1.99
     Bases
    1.82
    bases
    1.63
    Bases
    1.54
     Grundlage
    1.42
    Activations Density 0.081%

    No Known Activations