© 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. 2-GEMMASCOPE-RES-16K
    11. 4060
    Prev
    Next
    INDEX
    Explanations

    phrases that focus on the concept of possession or ownership

    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
     Brink
    -0.61
    RunWith
    -0.59
    മ്
    -0.53
    AfterClass
    -0.50
    äd
    -0.50
     Greenfield
    -0.49
     programmet
    -0.48
     ffilm
    -0.48
     Meksiku
    -0.48
    springframework
    -0.48
    POSITIVE LOGITS
    dozen
    1.00
    several
    0.87
     many
    0.84
    MANY
    0.84
    roek
    0.82
     several
    0.81
     wiele
    0.80
     FEW
    0.79
    few
    0.79
    öbb
    0.77
    Activations Density 0.487%

    No Known Activations