© 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. 5959
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "drop" or "dropping."

    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
    +#+
    -0.68
     contextLoads
    -0.65
    anthene
    -0.64
     geladeira
    -0.63
    EDEFAULT
    -0.60
    PreferredItem
    -0.60
    usitis
    -0.60
    Năm
    -0.59
    IUrlHelper
    -0.59
    inheritDoc
    -0.58
    POSITIVE LOGITS
     drop
    3.69
    drop
    3.48
     drops
    3.36
     Drop
    3.36
    Drop
    3.27
     DROP
    3.21
     dropping
    3.05
     dropped
    2.98
     Drops
    2.98
    drops
    2.96
    Activations Density 0.043%

    No Known Activations