© 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. 16006
    Prev
    Next
    INDEX
    Explanations

    phrases related to shutting down or silencing

    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
     Савезне
    -0.81
    IsMutable
    -0.80
    Бележки
    -0.80
    findpost
    -0.78
    Джерела
    -0.77
    évaluateur
    -0.73
     Eastwood
    -0.72
    WriteTagHelper
    -0.72
     rând
    -0.71
     Füßen
    -0.71
    POSITIVE LOGITS
     shut
    3.38
     Shut
    2.95
    shut
    2.81
     SHUT
    2.78
    Shut
    2.69
     shuts
    2.50
    SHUT
    2.39
     shutting
    2.32
     shutdown
    2.19
     Shutdown
    1.92
    Activations Density 0.046%

    No Known Activations