© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2943
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their relationships or roles in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases involving the word "which" and references to subjects or actions in a context of conditions or restrictions

    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
     contextLoads
    -0.80
     defaultstate
    -0.71
    BagLayout
    -0.66
    DrawerToggle
    -0.63
    UVWXYZ
    -0.62
    agisse
    -0.61
     Exactos
    -0.60
    anelas
    -0.59
    لفل
    -0.58
    Билгалдахарш
    -0.58
    POSITIVE LOGITS
    pulumi
    0.53
     whose
    0.48
     通販
    0.48
    […]
    0.47
    …)
    0.46
    numerusform
    0.45
     requiring
    0.45
     farm
    0.44
    dung
    0.44
    nonatomic
    0.43
    Activations Density 0.347%

    No Known Activations